Paper

The following are the latest papers (sorted by release date) on prompt engineering for large language models (LLMs). We update the list of papers on a daily/weekly basis.

Overviews

• The Prompt Report: A Systematic Survey of Prompting Techniques (June 2024)
• Prompt Design and Engineering: Introduction and Advanced Methods (January 2024)
• A Survey on Hallucination in Large Language Models: Principles,Taxonomy, Challenges, and Open Questions (November 2023)
• An RL Perspective on RLHF, Prompting, and Beyond (October 2023)
• Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation (May 2023)
• Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study (May 2023)
• Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond (April 2023)
• Tool Learning with Foundation Models (April 2023)
• One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era (April 2023)
• A Bibliometric Review of Large Language Models Research from 2017 to 2023 (April 2023)
• A Survey of Large Language Models (April 2023)
• Nature Language Reasoning, A Survey (March 2023)
• Augmented Language Models: a Survey(February 2023)
• A Survey for In-context Learning (December 2022)
• Towards Reasoning in Large Language Models: A Survey (December 2022)
• Reasoning with Language Model Prompting: A Survey (December 2022)
• Emergent Abilities of Large Language Models (June 2022)
• A Taxonomy of Prompt Modifiers for Text-To-Image Generation April 2022)
• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing) (July 2021)

Approaches

• Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic(February 2024)
• Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4 (December 2023)
• Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading (October 2023)
• Large Language Models as Analogical Reasoners (October 2023)
• LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models(October 2023)
• Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL (September 2023)
• Chain-of-Verification Reduces Hallucination in Large Language Models (September 2023)
• Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers (September 2023)
• From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting (September 2023)
• Re-Reading Improves Reasoning in Language Models (September 2023)
• Graph of Thoughts: Solving Elaborate Problems with Large Language Models (August 2023)
• Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding (July 2023)
• Focused Prefix Tuning for Controllable Text Generation (June 2023)
• Exploring Lottery Prompts for Pre-trained Language Models (May 2023)
• Less Likely Brainstorming: Using Language Models to Generate Alternative Hypotheses (May 2023)
• Let’s Verify Step by Step (May 2023)
• Universality and Limitations of Prompt Tuning (May 2023)
• MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting (May 2023)
• PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents) (May 2023)
• Reasoning with Language Model is Planning with World Model (May 2023)
• Self-Critique Prompting with Large Language Models for Inductive Instructions (May 2023)
• Better Zero-Shot Reasoning with Self-Adaptive Prompting (May 2023)
• Hierarchical Prompting Assists Large Language Model on Web Navigation (May 2023)
• Interactive Natural Language Processing (May 2023)
• Can We Edit Factual Knowledge by In-Context Learning? (May 2023)
• In-Context Learning of Large Language Models Explained as Kernel Regression (May 2023)
• Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models (May 2023)
• Meta-in-context learning in large language models (May 2023)
• Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning with LLMs) (May 2023)
• Post Hoc Explanations of Language Models Can Improve Language Models) (May 2023)
• Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt (May 2023)
• TreePrompt: Learning to Compose Tree Prompts for Explainable Visual Grounding (May 2023)
• TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks (May 2023)
• Efficient Prompting via Dynamic In-Context Learning (May 2023)
• The Web Can Be Your Oyster for Improving Large Language Models (May 2023)
• Flatness-Aware Prompt Selection Improves Accuracy and Sample Efficiency (May 2023)
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models (May 2023)
• ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs (May 2023)
• Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models (May 2023)
• CooK: Empowering General-Purpose Language Models with Modular and Collaborative Knowledge (May 2023)
• What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning (May 2023)
• Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling (May 2023)
• Satisfiability-Aided Language Models Using Declarative Prompting (May 2023)
• Pre-Training to Learn in Context (May 2023)
• Boosted Prompt Ensembles for Large Language Models (April 2023)
• Global Prompt Cell: A Portable Control Module for Effective Prompt (April 2023)
• Why think step-by-step? Reasoning emerges from the locality of experience (April 2023)
• Revisiting Automated Prompting: Are We Actually Doing Better? (April 2023)
• REFINER: Reasoning Feedback on Intermediate Representations (April 2023)
• Reflexion: an autonomous agent with dynamic memory and self-reflection (March 2023)
• CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society (March 2023)
• Self-Refine: Iterative Refinement with Self-Feedback (March 2023)
• kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference (March 2023)
• Visual-Language Prompt Tuning with Knowledge-guided Context Optimization (March 2023)
• Fairness-guided Few-shot Prompting for Large Language Models (March 2023)
• Context-faithful Prompting for Large Language Models (March 2023)
• Is Prompt All You Need? No. A Comprehensive and Broader View of Instruction Learning (March 2023)
• UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation (March 2023)
• Model-tuning Via Prompts Makes NLP Models Adversarially Robust) (March 2023)
• Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer (March 2023)
• CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification) (March 2023)
• Larger language models do in-context learning differently (March 2023)
• OpenICL: An Open-Source Framework for In-context Learning (March 2023)
• Dynamic Prompting: A Unified Framework for Prompt Tuning (March 2023)
• ART: Automatic multi-step reasoning and tool-use for large language models (March 2023)
• Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning (March 2023)
• Effectiveness of Data Augmentation for Prefix Tuning with Limited Data (March 2023)
• Mixture of Soft Prompts for Controllable Data Generation (March 2023)
• Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners(opens in a new tab) (March 2023)
• How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks(opens in a new tab) (March 2023)
• Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT(opens in a new tab) (February 2023)
• EvoPrompting: Language Models for Code-Level Neural Architecture Search(opens in a new tab) (February 2023)
• In-Context Instruction Learning(opens in a new tab) (February 2023)
• Chain of Hindsight Aligns Language Models with Feedback(opens in a new tab) (February 2023)
• Language Is Not All You Need: Aligning Perception with Language Models(opens in a new tab) (February 2023)
• Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data(opens in a new tab) (February 2023)
• Active Prompting with Chain-of-Thought for Large Language Models(opens in a new tab) (February 2023)
• More than you’ve asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models(opens in a new tab) (February 2023)
• A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT(opens in a new tab) (February 2023)
• Guiding Large Language Models via Directional Stimulus Prompting(opens in a new tab) (February 2023)
• How Does In-Context Learning Help Prompt Tuning?(opens in a new tab) (February 2023)
• Scalable Prompt Generation for Semi-supervised Learning with Language Models(opens in a new tab) (February 2023)
• Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints(opens in a new tab) (February 2023)
• À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting(opens in a new tab) (February 2023)
• GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks(opens in a new tab) (February 2023)
• The Capacity for Moral Self-Correction in Large Language Models(opens in a new tab) (February 2023)
• SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains(opens in a new tab) (February 2023)
• Evaluating the Robustness of Discrete Prompts(opens in a new tab) (February 2023)
• Compositional Exemplars for In-context Learning(opens in a new tab) (February 2023)
• Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery(opens in a new tab) (February 2023)
• Multimodal Chain-of-Thought Reasoning in Language Models(opens in a new tab) (February 2023)
• Large Language Models Can Be Easily Distracted by Irrelevant Context(opens in a new tab) (February 2023)
• Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models(opens in a new tab) (February 2023)
• Progressive Prompts: Continual Learning for Language Models(opens in a new tab) (January 2023)
• Batch Prompting: Efficient Inference with LLM APIs(opens in a new tab) (January 2023)
• Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP(opens in a new tab) (December 2022)
• On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning(opens in a new tab) (December 2022)
• Constitutional AI: Harmlessness from AI Feedback(opens in a new tab) (December 2022)
• Successive Prompting for Decomposing Complex Questions(opens in a new tab) (December 2022)
• Large Language Models are reasoners with Self-Verification(opens in a new tab) (December 2022)
• Discovering Language Model Behaviors with Model-Written Evaluations(opens in a new tab) (December 2022)
• Structured Prompting: Scaling In-Context Learning to 1,000 Examples(opens in a new tab) (December 2022)
• PAL: Program-aided Language Models(opens in a new tab) (November 2022)
• Large Language Models Are Human-Level Prompt Engineers(opens in a new tab) (November 2022)
• Ignore Previous Prompt: Attack Techniques For Language Models(opens in a new tab) (November 2022)
• Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods(opens in a new tab) (November 2022)
• Teaching Algorithmic Reasoning via In-context Learning(opens in a new tab) (November 2022)
• Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference(opens in a new tab) (November 2022)
• Ask Me Anything: A simple strategy for prompting language models(opens in a new tab) (October 2022)
• Recitation-Augmented Language Models(opens in a new tab) (October 2022)
• ReAct: Synergizing Reasoning and Acting in Language Models(opens in a new tab) (October 2022)
• Prompting GPT-3 To Be Reliable(opens in a new tab) (October 2022)
• Decomposed Prompting: A Modular Approach for Solving Complex Tasks(opens in a new tab) (October 2022)
• Automatic Chain of Thought Prompting in Large Language Models(opens in a new tab) (October 2022)
• Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought(opens in a new tab) (October 2022)
• Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples(opens in a new tab) (September 2022)
• Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning(opens in a new tab) (September 2022)
• Promptagator: Few-shot Dense Retrieval From 8 Examples(opens in a new tab) (September 2022)
• Atlas: Few-shot Learning with Retrieval Augmented Language Models(opens in a new tab) (November 2022)
• DocPrompting: Generating Code by Retrieving the Docs(opens in a new tab) (July 2022)
• On the Advance of Making Language Models Better Reasoners(opens in a new tab) (June 2022)
• Large Language Models are Zero-Shot Reasoners(opens in a new tab) (May 2022)
• Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations(opens in a new tab) (May 2022)
• MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning(opens in a new tab) (May 2022)
• PPT: Pre-trained Prompt Tuning for Few-shot Learning(opens in a new tab) (Mqy 2022)
• Toxicity Detection with Generative Prompt-based Inference(opens in a new tab) (May 2022)
• Learning to Transfer Prompts for Text Generation(opens in a new tab) (May 2022)
• The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning(opens in a new tab) (May 2022)
• A Taxonomy of Prompt Modifiers for Text-To-Image Generation(opens in a new tab) (April 2022)
• PromptChainer: Chaining Large Language Model Prompts through Visual Programming(opens in a new tab) (March 2022)
• Self-Consistency Improves Chain of Thought Reasoning in Language Models(opens in a new tab) (March 2022)
• Training language models to follow instructions with human feedback(opens in a new tab)
• Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?(opens in a new tab) (February 2022)
• Chain of Thought Prompting Elicits Reasoning in Large Language Models(opens in a new tab) (January 2022)
• Show Your Work: Scratchpads for Intermediate Computation with Language Models(opens in a new tab) (November 2021)
• AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts(opens in a new tab) (October 2021)
• Generated Knowledge Prompting for Commonsense Reasoning(opens in a new tab) (October 2021)
• Multitask Prompted Training Enables Zero-Shot Task Generalization(opens in a new tab) (October 2021)
• Reframing Instructional Prompts to GPTk’s Language(opens in a new tab) (September 2021)
• Design Guidelines for Prompt Engineering Text-to-Image Generative Models(opens in a new tab) (September 2021)
• Making Pre-trained Language Models Better Few-shot Learners(opens in a new tab) (August 2021)
• Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity(opens in a new tab) (April 2021)
• BERTese: Learning to Speak to BERT(opens in a new tab) (April 2021)
• The Power of Scale for Parameter-Efficient Prompt Tuning(opens in a new tab) (April 2021)
• Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm(opens in a new tab) (February 2021)
• Calibrate Before Use: Improving Few-Shot Performance of Language Models(opens in a new tab) (February 2021)
• Prefix-Tuning: Optimizing Continuous Prompts for Generation(opens in a new tab) (January 2021)
• Learning to Generate Task-Specific Adapters from Task Description(opens in a new tab) (January 2021)
• Making Pre-trained Language Models Better Few-shot Learners(opens in a new tab) (December 2020)
• Learning from Task Descriptions(opens in a new tab) (November 2020)
• AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts(opens in a new tab) (October 2020)
• Language Models are Few-Shot Learners(opens in a new tab) (May 2020)
• How Can We Know What Language Models Know?(opens in a new tab) (July 2020)
• Scaling Laws for Neural Language Models(opens in a new tab) (January 2020)

Applications

• PromptRE: Weakly-Supervised Document-Level Relation Extraction via Prompting-Based Data Programming(opens in a new tab) (October 2023)
• Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation(opens in a new tab) (October 2023)
• Who Wrote it and Why? Prompting Large-Language Models for Authorship Verification(opens in a new tab) (October 2023)
• Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques(opens in a new tab) (October 2023)
• Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models(opens in a new tab) (October 2023)
• From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting(opens in a new tab) (September 2023)
• Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation(opens in a new tab) (October 2023)
• Think before you speak: Training Language Models With Pause Tokens(opens in a new tab) (October 2023)
• (Dynamic) Prompting might be all you need to repair Compressed LLMs(opens in a new tab) (October 2023)
• In-Context Learning in Large Language Models: A Neuroscience-inspired Analysis of Representations(opens in a new tab) (September 2023)
• Understanding In-Context Learning from Repetitions(opens in a new tab) (September 2023)
• Investigating the Efficacy of Large Language Models in Reflective Assessment Methods through Chain of Thoughts Prompting(opens in a new tab) (September 2023)
• Automatic Prompt Rewriting for Personalized Text Generation(opens in a new tab) (September 2023)
• Efficient Streaming Language Models with Attention Sinks(opens in a new tab) (September 2023)
• The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)(opens in a new tab) (September 2023)
• Graph Neural Prompting with Large Language Models(opens in a new tab) (September 2023)
• Large Language Model Alignment: A Survey(opens in a new tab) (September 2023)
• Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic(opens in a new tab) (September 2023)
• A Practical Survey on Zero-shot Prompt Design for In-context Learning(opens in a new tab) (September 2023)
• EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning(opens in a new tab) (September 2023)
• Prompt, Condition, and Generate: Classification of Unsupported Claims with In-Context Learning(opens in a new tab) (September 2023)
• PolicyGPT: Automated Analysis of Privacy Policies with Large Language Models(opens in a new tab) (September 2023)
• LLM4Jobs: Unsupervised occupation extraction and standardization leveraging Large Language Models(opens in a new tab) (September 2023)
• Summarization is (Almost) Dead(opens in a new tab) (September 2023)
• Investigating Zero- and Few-shot Generalization in Fact Verification(opens in a new tab) (September 2023)
• Performance of the Pre-Trained Large Language Model GPT-4 on Automated Short Answer Grading(opens in a new tab) (September 2023)
• Contrastive Decoding Improves Reasoning in Large Language Models(opens in a new tab) (September 2023)
• Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?(opens in a new tab) (September 2023)
• Neural Machine Translation Models Can Learn to be Few-shot Learners(opens in a new tab) (September 2023)
• Chain-of-Thought Reasoning is a Policy Improvement Operator(opens in a new tab) (September 2023)
• ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer(opens in a new tab) (September 2023)
• When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets(opens in a new tab) (September 2023)
• Using Large Language Models for Knowledge Engineering (LLMKE): A Case Study on Wikidata(opens in a new tab) (September 2023)
• Self-Consistent Narrative Prompts on Abductive Natural Language Inference(opens in a new tab) (September 2023)
• Investigating Answerability of LLMs for Long-Form Question Answering(opens in a new tab) (September 2023)
• PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions(opens in a new tab) (September 2023)
• An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing(opens in a new tab) (September 2023)
• Leveraging Contextual Information for Effective Entity Salience Detection(opens in a new tab) (September 2023)
• Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts(opens in a new tab) (September 2023)
• PACE: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis(opens in a new tab) (September 2023)
• From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting(opens in a new tab) (September 2023)
• Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models(opens in a new tab) (September 2023)
• Zero-Resource Hallucination Prevention for Large Language Models(opens in a new tab) (September 2023)
• Certifying LLM Safety against Adversarial Prompting(opens in a new tab) (September 2023)
• Improving Code Generation by Dynamic Temperature Sampling(opens in a new tab) (September 2023)
• Prompting a Large Language Model to Generate Diverse Motivational Messages: A Comparison with Human-Written Messages(opens in a new tab) (August 2023)
• Financial News Analytics Using Fine-Tuned Llama 2 GPT Model(opens in a new tab) (August 2023)
• A Study on Robustness and Reliability of Large Language Model Code Generation(opens in a new tab) (August 2023)
• Large Language Models Vote: Prompting for Rare Disease Identification(opens in a new tab) (August 2023)
• WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct(opens in a new tab) (August 2023)
• Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning(opens in a new tab) (August 2023)
• Graph of Thoughts: Solving Elaborate Problems with Large Language Models(opens in a new tab) (August 2023)
• Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment(opens in a new tab) (August 2023)
• Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought(opens in a new tab) (August 2023)
• You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content(opens in a new tab) (August 2023)
• LLM As DBA(opens in a new tab) (August 2023)
• Interpretable Math Word Problem Solution Generation Via Step-by-step Planning(opens in a new tab) (June 2023)
• In-Context Learning User Simulators for Task-Oriented Dialog Systems(opens in a new tab) (June 2023)
• SQL-PaLM: Improved Large Language ModelAdaptation for Text-to-SQL(opens in a new tab) (June 2023)
• Effective Structured Prompting by Meta-Learning and Representative Verbalizer(opens in a new tab) (June 2023)
• Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering(opens in a new tab) (June 2023)
• Chain-Of-Thought Prompting Under Streaming Batch: A Case Study(opens in a new tab) (June 2023)
• Red Teaming Language Model Detectors with Language Models(opens in a new tab) (May 2023)
• Gorilla: Large Language Model Connected with Massive APIs(opens in a new tab) (May 2023)
• Deliberate then Generate: Enhanced Prompting Framework for Text Generation(opens in a new tab) (May 2023)
• What does the Failure to Reason with “Respectively” in Zero/Few-Shot Settings Tell Us about Language Models?(opens in a new tab) (May 2023)
• ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning(opens in a new tab) (May 2023)
• SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models(opens in a new tab) (May 2023)
• Grammar Prompting for Domain-Specific Language Generation with Large Language Models(opens in a new tab) (May 2023)
• Mitigating Label Biases for In-context Learning(opens in a new tab) (May 2023)
• Short Answer Grading Using One-shot Prompting and Text Similarity Scoring Model(opens in a new tab) (May 2023)
• Strategic Reasoning with Language Models(opens in a new tab) (May 2023)
• Dissecting Chain-of-Thought: A Study on Compositional In-Context Learning of MLPs(opens in a new tab) (May 2023)
• Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models(opens in a new tab) (May 2023)
• Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning(opens in a new tab) (May 2023)
• Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods(opens in a new tab) (May 2023)
• NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models(opens in a new tab) (May 2023)
• Tab-CoT: Zero-shot Tabular Chain of Thought(opens in a new tab) (May 2023)
• Evaluating GPT-3 Generated Explanations for Hateful Content Moderation(opens in a new tab) (May 2023)
• Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks(opens in a new tab) (May 2023)
• [Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning]https://arxiv.org/abs/2305.17373(opens in a new tab)) (May 2023)
• Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models’ Reasoning Performance(opens in a new tab) (May 2023)
• Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning(opens in a new tab) (May 2023)
• Heterogeneous Value Evaluation for Large Language Models(opens in a new tab) (May 2023)
• PromptNER: Prompt Locating and Typing for Named Entity Recognition(opens in a new tab) (May 2023)
• Small Language Models Improve Giants by Rewriting Their Outputs(opens in a new tab) (May 2023)
• On the Planning Abilities of Large Language Models — A Critical Investigation(opens in a new tab) (May 2023)
• Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Large Language Models(opens in a new tab) (May 2023)
• PRODIGY: Enabling In-context Learning Over Graphs(opens in a new tab) (May 2023)
• Large Language Models are Few-Shot Health Learners(opens in a new tab) (May 2023)
• Role-Play with Large Language Models(opens in a new tab) (May 2023)
• Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations(opens in a new tab) (May 2023)
• Fact-Checking Complex Claims with Program-Guided Reasoning(opens in a new tab) (May 2023)
• Large Language Models as Tool Makers(opens in a new tab) (May 2023)
• Iterative Forward Tuning Boosts In-context Learning in Language Models(opens in a new tab) (May 2023)
• SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks(opens in a new tab) (May 2023)
• Interactive Natural Language Processing(opens in a new tab) (May 2023)
• An automatically discovered chain-of-thought prompt generalizes to novel models and datasets(opens in a new tab) (May 2023)
• Large Language Model Guided Tree-of-Thought(opens in a new tab) (May 2023)
• Active Retrieval Augmented Generation(opens in a new tab) (May 2023)
• A PhD Student’s Perspective on Research in NLP in the Era of Very Large Language Models(opens in a new tab) (May 2023)
• Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings(opens in a new tab) (May 2023)
• Mirages: On Anthropomorphism in Dialogue Systems(opens in a new tab) (May 2023)
• Model evaluation for extreme risks(opens in a new tab) (May 2023)
• Language Models Don’t Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting(opens in a new tab) (May 2023)
• Cognitive Reframing of Negative Thoughts through Human-Language Model Interaction(opens in a new tab) (May 2023)
• PromptClass: Weakly-Supervised Text Classification with Prompting Enhanced Noise-Robust Self-Training(opens in a new tab) (May 2023)
• Augmented Large Language Models with Parametric Knowledge Guiding(opens in a new tab) (May 2023)
• Aligning Large Language Models through Synthetic Feedback(opens in a new tab) (May 2023)
• Concept-aware Training Improves In-context Learning Ability of Language Models(opens in a new tab) (May 2023)
• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance(opens in a new tab) (May 2023)
• Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation(opens in a new tab) (May 2023)
• Detecting automatically the layout of clinical documents to enhance the performances of downstream natural language processing(opens in a new tab) (May 2023)
• “Is the Pope Catholic?” Applying Chain-of-Thought Reasoning to Understanding Conversational Implicatures(opens in a new tab) (May 2023)
• Let’s Think Frame by Frame: Evaluating Video Chain of Thought with Video Infilling and Prediction(opens in a new tab) (May 2023)
• Generating Data for Symbolic Language with Large Language Models(opens in a new tab) (May 2023)
• Make a Choice! Knowledge Base Question Answering with In-Context Learning(opens in a new tab) (May 2023)
• Improving Language Models via Plug-and-Play Retrieval Feedback(opens in a new tab) (May 2023)
• Multi-Granularity Prompts for Topic Shift Detection in Dialogue(opens in a new tab) (May 2023)
• The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning(opens in a new tab) (May 2023)
• Can Language Models Understand Physical Concepts?(opens in a new tab) (May 2023)
• Evaluating Factual Consistency of Summaries with Large Language Models(opens in a new tab) (May 2023)
• Dr.ICL: Demonstration-Retrieved In-context Learning(opens in a new tab) (May 2023)
• Probing in Context: Toward Building Robust Classifiers via Probing Large Language Models(opens in a new tab) (May 2023)
• Skill-Based Few-Shot Selection for In-Context Learning(opens in a new tab) (May 2023)
• Exploring Chain-of-Thought Style Prompting for Text-to-SQL(opens in a new tab) (May 2023)
• Enhancing Chat Language Models by Scaling High-quality Instructional Conversations(opens in a new tab) (May 2023)
• On Learning to Summarize with Large Language Models as References(opens in a new tab) (May 2023)
• Learning to Generate Novel Scientific Directions with Contextualized Literature-based Discovery(opens in a new tab) (May 2023)
• Active Learning Principles for In-Context Learning with Large Language Models(opens in a new tab) (May 2023)
• Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs(opens in a new tab) (May 2023)
• Improving Factuality and Reasoning in Language Models through Multiagent Debate(opens in a new tab) (May 2023)
• ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on\ Chat-based Large Language Models(opens in a new tab) (May 2023)
• WikiChat: A Few-Shot LLM-Based Chatbot Grounded with Wikipedia(opens in a new tab) (May 2023)
• Query Rewriting for Retrieval-Augmented Large Language Models(opens in a new tab) (May 2023)
• Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker(opens in a new tab) (May 2023)
• Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method(opens in a new tab) (May 2023)
• Small Language Models Improve Giants by Rewriting Their Outputs(opens in a new tab) (May 2023)
• Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration(opens in a new tab) (May 2023)
• Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning(opens in a new tab) (May 2023)
• Mitigating Language Model Hallucination with Interactive Question-Knowledge Alignment(opens in a new tab) (May 2023)
• Making Language Models Better Tool Learners with Execution Feedback(opens in a new tab) (May 2023)
• Text-to-SQL Error Correction with Language Models of Code(opens in a new tab) (May 2023)
• Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models(opens in a new tab) (May 2023)
• SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations(opens in a new tab) (May 2023)
• “According to …” Prompting Language Models Improves Quoting from Pre-Training Data(opens in a new tab) (May 2023)
• Prompt-based methods may underestimate large language models’ linguistic generalizations(opens in a new tab) (May 2023)
• Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases(opens in a new tab) (May 2023)
• Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations(opens in a new tab) (May 2023)
• Automated Few-shot Classification with Instruction-Finetuned Language Models(opens in a new tab) (May 2023)
• Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies(opens in a new tab) (May 2023)
• MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction(opens in a new tab) (May 2023)
• Learning Interpretable Style Embeddings via Prompting LLMs(opens in a new tab) (May 2023)
• Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting(opens in a new tab) (May 2023)
• Fact-Checking Complex Claims with Program-Guided Reasoning(opens in a new tab) (May 2023)
• A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches(opens in a new tab) (May 2023)
• This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models(opens in a new tab) (May 2023)
• Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer(opens in a new tab) (May 2023)
• Evaluating Prompt-based Question Answering for Object Prediction in the Open Research Knowledge Graph(opens in a new tab) (May 2023)
• Explaining How Transformers Use Context to Build Predictions(opens in a new tab) (May 2023)
• PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs(opens in a new tab) (May 2023)
• PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Search(opens in a new tab) (May 2023)
• Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning(opens in a new tab) (May 2023)
• Enhancing Few-shot NER with Prompt Ordering based Data Augmentation(opens in a new tab) (May 2023)
• Chain-of-thought prompting for responding to in-depth dialogue questions with LLM(opens in a new tab) (May 2023)
• How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings(opens in a new tab) (May 2023)
• Evaluation of medium-large Language Models at zero-shot closed book generative question answering(opens in a new tab) (May 2023)
• Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer(opens in a new tab) (May 2023)
• Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?(opens in a new tab) (May 2023)
• Reasoning Implicit Sentiment with Chain-of-Thought Prompting(opens in a new tab) (May 2023)
• Writing your own book: A method for going from closed to open book QA to improve robustness and performance of smaller LLMs(opens in a new tab) (May 2023)
• AutoTrial: Prompting Language Models for Clinical Trial Design(opens in a new tab) (May 2023)
• CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing(opens in a new tab) (May 2023)
• Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning(opens in a new tab) (May 2023)
• Prompting with Pseudo-Code Instructions(opens in a new tab) (May 2023)
• TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models(opens in a new tab) (May 2023)
• Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors(opens in a new tab) (May 2023)
• Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model(opens in a new tab) (May 2023)
• Learning In-context Learning for Named Entity Recognition(opens in a new tab) (May 2023)
• Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation(opens in a new tab) (May 2023)
• TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition(opens in a new tab) (May 2023)
• Large Language Models can be Guided to Evade AI-Generated Text Detection(opens in a new tab) (May 2023)
• Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning(opens in a new tab) (May 2023)
• Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization(opens in a new tab) (May 2023)
• Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation(opens in a new tab) (May 2023)
• Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback(opens in a new tab) (May 2023)
• ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing(opens in a new tab) (May 2023)
• StructGPT: A General Framework for Large Language Model to Reason over Structured Data(opens in a new tab) (May 2023)
• Towards Expert-Level Medical Question Answering with Large Language Models(opens in a new tab) (May 2023)
• Large Language Models are Built-in Autoregressive Search Engines(opens in a new tab) (May 2023)
• MsPrompt: Multi-step Prompt Learning for Debiasing Few-shot Event Detection(opens in a new tab) (May 2023)
• Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation(opens in a new tab) (May 2023)
• SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting(opens in a new tab) (May 2023)
• Multi-modal Visual Understanding with Prompts for Semantic Information Disentanglement of Image(opens in a new tab) (May 2023)
• Soft Prompt Decoding for Multilingual Dense Retrieval(opens in a new tab) (May 2023)
• PaLM 2 Technical Report(opens in a new tab) (May 2023)
• Are LLMs All You Need for Task-Oriented Dialogue?(opens in a new tab) (April 2023)
• HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting(opens in a new tab) (April 2023)
• Approximating Human Evaluation of Social Chatbots with Prompting(opens in a new tab) (April 2023)
• Automated Reading Passage Generation with OpenAI’s Large Language Model(opens in a new tab) (April 2023)
• WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus(opens in a new tab) (April 2023)
• Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition(opens in a new tab) (April 2023)
• GPT detectors are biased against non-native English writers(opens in a new tab) (April 2023)
• Zero-Shot Next-Item Recommendation using Large Pretrained Language Models(opens in a new tab) (April 2023)
• Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT(opens in a new tab) (April 2023)
• Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning(opens in a new tab) (April 2023)
• Better Language Models of Code through Self-Improvement(opens in a new tab) (April 2023)
• PromptORE — A Novel Approach Towards Fully Unsupervised Relation Extraction(opens in a new tab) (April 2023)
• Assessing Language Model Deployment with Risk Cards (April 2023)
• Enhancing Large Language Models with Climate Resources(opens in a new tab) (March 2023)
• BloombergGPT: A Large Language Model for Finance(opens in a new tab) (March 2023)
• Medical Intervention Duration Estimation Using Language-enhanced Transformer Encoder with Medical Prompts(opens in a new tab) (March 2023)
• Soft-prompt tuning to predict lung cancer using primary care free-text Dutch medical notes(opens in a new tab) (March 2023)
• TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs(opens in a new tab) (March 2023)
• Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning(opens in a new tab) (March 2023)
• Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses(opens in a new tab) (March 2023)
• Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning(opens in a new tab) (March 2023)
• Debiasing Scores and Prompts of 2D Diffusion for Robust Text-to-3D Generation(opens in a new tab) (March 2023)
• Zero-shot Model Diagnosis(opens in a new tab) (March 2023)
• Prompting Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages(opens in a new tab) (March 2023)
• SPeC: A Soft Prompt-Based Calibration on Mitigating Performance Variability in Clinical Notes Summarization(opens in a new tab) (March 2023)
• Large Language Models and Simple, Stupid Bugs(opens in a new tab) (March 2023)
• Can Generative Pre-trained Transformers (GPT) Pass Assessments in Higher Education Programming Courses?(opens in a new tab) (March 2023)
• SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models(opens in a new tab) (March 2023)
• Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification(opens in a new tab) (March 2023)
• ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction(opens in a new tab) (March 2023)
• MathPrompter: Mathematical Reasoning using Large Language Models(opens in a new tab) (March 2023)
• Prompt-Based Learning for Thread Structure Prediction in Cybersecurity Forums(opens in a new tab) (March 2023)
• Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting(opens in a new tab) (March 2023)
• Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering(opens in a new tab) (March 2023)
• Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysis(opens in a new tab) (March 2023)
• SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks(opens in a new tab) (March 2023)
• Goal Driven Discovery of Distributional Differences via Language Descriptions(opens in a new tab) (February 2023)
• Navigating the Grey Area: Expressions of Overconfidence and Uncertainty in Language Models(opens in a new tab) (February 2023)
• TabGenie: A Toolkit for Table-to-Text Generation(opens in a new tab) (February 2023)
• SGL-PT: A Strong Graph Learner with Graph Prompt Tuning(opens in a new tab) (February 2023)
• Few-Shot Table-to-Text Generation with Prompt-based Adapter(opens in a new tab) (February 2023)
• Language Models Are Few-shot Learners for Prognostic Prediction(opens in a new tab) (February 2023)
• STA: Self-controlled Text Augmentation for Improving Text Classifications(opens in a new tab) (February 2023)
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback(opens in a new tab) (February 2023)
• How Generative AI models such as ChatGPT can be (Mis)Used in SPC Practice, Education, and Research? An Exploratory Study(opens in a new tab) (February 2023)
• Grimm in Wonderland: Prompt Engineering with Midjourney to Illustrate Fairytales(opens in a new tab) (February 2023)
• LabelPrompt: Effective Prompt-based Learning for Relation Classification(opens in a new tab) (February 2023)
• Language Model Crossover: Variation through Few-Shot Prompting(opens in a new tab) (February 2023)
• Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition(opens in a new tab) (February 2023)
• The Capacity for Moral Self-Correction in Large Language Models(opens in a new tab) (February 2023)
• Prompting for Multimodal Hateful Meme Classification(opens in a new tab) (February 2023)
• PLACES: Prompting Language Models for Social Conversation Synthesis(opens in a new tab) (February 2023)
• Toolformer: Language Models Can Teach Themselves to Use Tools(opens in a new tab) (February 2023)
• Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation(opens in a new tab) (February 2023)
• Crawling the Internal Knowledge-Base of Language Models(opens in a new tab) (January 2023)
• Legal Prompt Engineering for Multilingual Legal Judgement Prediction(opens in a new tab) (December 2022)
• Investigating Prompt Engineering in Diffusion Models(opens in a new tab) (November 2022)
• Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering(opens in a new tab) (September 2022)
• Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Language(opens in a new tab) (October 2022)
• Piloting Copilot and Codex: Hot Temperature, Cold Prompts, or Black Magic?(opens in a new tab) (October 2022)
• Plot Writing From Scratch Pre-Trained Language Models(opens in a new tab) (July 2022)
• Survey of Hallucination in Natural Language Generation(opens in a new tab) (February 2022)

Collections

• Chain-of-Thought Papers(opens in a new tab)
• Papers with Code(opens in a new tab)
• Prompt Papers(opens in a new tab)