{"total":125,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459,"area":"lr"},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807,"area":"lr"},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596,"area":"lr"},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274,"area":"agents"},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249,"area":null},{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232,"area":null},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169,"area":"lr"},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148,"area":"lr"},{"id":"2305.03268","title":"Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework","created":"2023-05-05","cited_by_count":139,"area":"lr"},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2210.06726","title":"Explanations from Large Language Models Make Small Reasoners Better","created":"2022-10-13","cited_by_count":124,"area":"lr"},{"id":"2207.00747","title":"Rationale-Augmented Ensembles in Language Models","created":"2022-07-02","cited_by_count":111,"area":null},{"id":"2305.08377","title":"Text Classification via Large Language Models","created":"2023-05-15","cited_by_count":106,"area":null},{"id":"2305.01879","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","created":"2023-05-03","cited_by_count":105,"area":"lr"},{"id":"2308.06595","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","created":"2023-08-12","cited_by_count":102,"area":"mllm"},{"id":"2209.06293","title":"Do Androids Laugh at Electric Sheep? Humor \"Understanding\" Benchmarks from The New Yorker Caption Contest","created":"2022-09-13","cited_by_count":98,"area":null},{"id":"2210.11584","title":"Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations","created":"2022-10-20","cited_by_count":85,"area":null},{"id":"2205.12404","title":"FLUTE: Figurative Language Understanding through Textual Explanations","created":"2022-05-24","cited_by_count":79,"area":null},{"id":"2307.03875","title":"Large Language Models for Supply Chain Optimization","created":"2023-07-08","cited_by_count":64,"area":null},{"id":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56,"area":"lr"},{"id":"2307.16883","title":"HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution","created":"2023-07-31","cited_by_count":56,"area":null},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48,"area":null},{"id":"2305.17680","title":"Evaluating GPT-3 Generated Explanations for Hateful Content Moderation","created":"2023-05-28","cited_by_count":46,"area":null},{"id":"2305.05252","title":"Distilling Script Knowledge from Large Language Models for Constrained Language Planning","created":"2023-05-09","cited_by_count":45,"area":null},{"id":"2502.08554","title":"Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies","created":"2025-02-12","cited_by_count":39,"area":null},{"id":"2305.07095","title":"Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales","created":"2023-05-11","cited_by_count":37,"area":null},{"id":"2311.00321","title":"HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning","created":"2023-11-01","cited_by_count":31,"area":null},{"id":"2404.09982","title":"INMS: Memory Sharing for Large Language Model based Agents","created":"2024-04-15","cited_by_count":31,"area":"agents"},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2402.10532","title":"Properties and Challenges of LLM-Generated Explanations","created":"2024-02-16","cited_by_count":24,"area":null},{"id":"2210.04982","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","created":"2022-10-10","cited_by_count":22,"area":null},{"id":"2305.14492","title":"Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment","created":"2023-05-23","cited_by_count":22,"area":null},{"id":"2405.06800","title":"LLM-Generated Black-box Explanations Can Be Adversarially Helpful","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2502.17898","title":"VeriPlan: Integrating Formal Verification and LLMs into End-User Planning","created":"2025-02-25","cited_by_count":20,"area":null},{"id":"2209.10372","title":"WeLM: A Well-Read Pre-trained Language Model for Chinese","created":"2022-09-21","cited_by_count":19,"area":null},{"id":"2405.01474","title":"Understanding Figurative Meaning through Explainable Visual Entailment","created":"2024-05-02","cited_by_count":19,"area":"mllm"},{"id":"2212.10467","title":"Generic Temporal Reasoning with Differential Analysis and Explanation","created":"2022-12-20","cited_by_count":18,"area":"lr"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2310.17876","title":"TarGEN: Targeted Data Generation with Large Language Models","created":"2023-10-27","cited_by_count":17,"area":null},{"id":"2406.19482","title":"xTower: A Multilingual LLM for Explaining and Correcting Translation Errors","created":"2024-06-27","cited_by_count":17,"area":null},{"id":"2306.09299","title":"Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization","created":"2023-06-15","cited_by_count":16,"area":"agents"},{"id":"2310.13850","title":"Ecologically Valid Explanations for Label Variation in NLI","created":"2023-10-20","cited_by_count":16,"area":null},{"id":"2401.12576","title":"LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations","created":"2024-01-23","cited_by_count":16,"area":null},{"id":"2406.07212","title":"Trustworthy and Practical AI for Healthcare: A Guided Deferral System with Large Language Models","created":"2024-06-11","cited_by_count":16,"area":null},{"id":"2406.14511","title":"Investigating Mysteries of CoT-Augmented Distillation","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2310.15431","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2310.11878","title":"From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification","created":"2023-10-18","cited_by_count":14,"area":null},{"id":"2206.11083","title":"Investigating the Benefits of Free-Form Rationales","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2210.07222","title":"Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2305.17696","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2211.00614","title":"Natural Language Deduction with Incomplete Information","created":"2022-11-01","cited_by_count":12,"area":null},{"id":"2302.09715","title":"What happens before and after: Multi-Event Commonsense in Event Coreference Resolution","created":"2023-02-20","cited_by_count":12,"area":null},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2305.12723","title":"Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2310.14159","title":"Can Language Models Laugh at YouTube Short-form Videos?","created":"2023-10-22","cited_by_count":11,"area":null},{"id":"2305.12945","title":"ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2306.08042","title":"FLamE: Few-shot Learning from Natural Language Explanations","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2406.04215","title":"mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans","created":"2024-06-06","cited_by_count":10,"area":"lr"},{"id":"2505.19428","title":"Frictional Agent Alignment Framework: Slow Down and Don't Break Things","created":"2025-05-26","cited_by_count":10,"area":"agents"},{"id":"2311.05085","title":"Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2412.13942","title":"A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2305.07355","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2410.04838","title":"Rationale-Aware Answer Verification by Pairwise Self-Evaluation","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2206.06029","title":"Mediators: Conversational Agents Explaining NLP Model Behavior","created":"2022-06-13","cited_by_count":7,"area":null},{"id":"2211.07517","title":"Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations","created":"2022-11-14","cited_by_count":7,"area":null},{"id":"2309.11439","title":"Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction","created":"2023-09-20","cited_by_count":7,"area":null},{"id":"2403.00462","title":"LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues","created":"2024-03-01","cited_by_count":7,"area":null},{"id":"2406.00343","title":"Beyond Metrics: Evaluating LLMs' Effectiveness in Culturally Nuanced, Low-Resource Real-World Scenarios","created":"2024-06-01","cited_by_count":7,"area":null},{"id":"2211.06499","title":"Social Construction of XAI: Do We Need One Definition to Rule Them All?","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2307.05082","title":"OntoChatGPT Information System: Ontology-Driven Structured Prompts for ChatGPT Meta-Learning","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2406.12645","title":"Evaluating Evidence Attribution in Generated Fact Checking Explanations","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2502.13321","title":"Adjust for Trust: Mitigating Trust-Induced Inappropriate Reliance on AI Assistance","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2502.18331","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","created":"2025-02-22","cited_by_count":6,"area":null},{"id":"2504.15848","title":"Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2211.11160","title":"Unsupervised Explanation Generation via Correct Instantiations","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2304.12443","title":"Understanding and Predicting Human Label Variation in Natural Language Inference through Explanation","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2305.11480","title":"CCGen: Explainable Complementary Concept Generation in E-Commerce","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2305.11789","title":"Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2308.04041","title":"InfeRE: Step-by-Step Regex Generation via Chain of Inference","created":"2023-08-08","cited_by_count":5,"area":null},{"id":"2309.08583","title":"ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer","created":"2023-09-15","cited_by_count":5,"area":"alignment"},{"id":"2310.06111","title":"BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2501.03857","title":"Progressive Document-level Text Simplification via Large Language Models","created":"2025-01-07","cited_by_count":5,"area":null},{"id":"2212.09603","title":"Explanation Regeneration via Information Bottleneck","created":"2022-12-19","cited_by_count":4,"area":null},{"id":"2308.16763","title":"Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection","created":"2023-08-31","cited_by_count":4,"area":"lr"},{"id":"2311.07099","title":"Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2401.15535","title":"Quantifying Stereotypes in Language","created":"2024-01-28","cited_by_count":4,"area":null},{"id":"2408.12748","title":"SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection","created":"2024-08-22","cited_by_count":4,"area":null},{"id":"2309.10346","title":"Explaining Agent Behavior with Large Language Models","created":"2023-09-19","cited_by_count":3,"area":"agents"},{"id":"2310.18358","title":"A Communication Theory Perspective on Prompting Engineering Methods for Large Language Models","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2311.18062","title":"Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation","created":"2023-11-29","cited_by_count":3,"area":"agents"},{"id":"2402.18016","title":"User Decision Guidance with Selective Explanation Presentation from Explainable-AI","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2505.19299","title":"A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2509.11026","title":"Rethinking Human Preference Evaluation of LLM Rationales","created":"2025-09-14","cited_by_count":3,"area":"lr"},{"id":"2509.13869","title":"Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs","created":"2025-09-17","cited_by_count":3,"area":"alignment"},{"id":"2510.01048","title":"Interpreting Language Models Through Concept Descriptions: A Survey","created":"2025-10-01","cited_by_count":3,"area":"mechinterp"}],"next_cursor":"100"}