{"total":126,"rows":[{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2201.06796","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","created":"2022-01-18","cited_by_count":249,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196,"area":"lr"},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125,"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":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2402.04614","title":"Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models","created":"2024-02-07","cited_by_count":105,"area":null},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"area":null},{"id":"2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","created":"2024-02-19","cited_by_count":71,"area":null},{"id":"2210.12329","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","created":"2022-10-22","cited_by_count":67,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2310.12558","title":"Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong","created":"2023-10-19","cited_by_count":51,"area":null},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45,"area":null},{"id":"2204.13074","title":"Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement","created":"2022-04-27","cited_by_count":37,"area":"lr"},{"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":"2405.01379","title":"Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving","created":"2024-05-02","cited_by_count":35,"area":null},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2106.11988","title":"On the Diversity and Limits of Human Explanations","created":"2021-06-22","cited_by_count":30,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2404.03189","title":"The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models","created":"2024-04-04","cited_by_count":29,"area":null},{"id":"2203.08480","title":"E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning","created":"2022-03-16","cited_by_count":28,"area":"lr"},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"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":"2401.09760","title":"A Comparative Study on Annotation Quality of Crowdsourcing and LLM via Label Aggregation","created":"2024-01-18","cited_by_count":23,"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":"2307.03859","title":"MDACE: MIMIC Documents Annotated with Code Evidence","created":"2023-07-07","cited_by_count":19,"area":null},{"id":"2212.10467","title":"Generic Temporal Reasoning with Differential Analysis and Explanation","created":"2022-12-20","cited_by_count":18,"area":"lr"},{"id":"2305.13214","title":"Atomic Inference for NLI with Generated Facts as Atoms","created":"2023-05-22","cited_by_count":18,"area":null},{"id":"2205.02593","title":"METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation","created":"2022-05-05","cited_by_count":17,"area":"lr"},{"id":"2112.08907","title":"Inherently Explainable Reinforcement Learning in Natural Language","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2305.02556","title":"Faithful Question Answering with Monte-Carlo Planning","created":"2023-05-04","cited_by_count":16,"area":"lr"},{"id":"2509.09396","title":"LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations","created":"2025-09-11","cited_by_count":16,"area":"synth"},{"id":"2105.10172","title":"Explainable Machine Learning with Prior Knowledge: An Overview","created":"2021-05-21","cited_by_count":15,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2204.08892","title":"A survey on improving NLP models with human explanations","created":"2022-04-19","cited_by_count":15,"area":null},{"id":"2212.01060","title":"Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning","created":"2022-12-02","cited_by_count":15,"area":null},{"id":"2305.14250","title":"Language Models with Rationality","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2306.13041","title":"Towards Explainable Evaluation Metrics for Machine Translation","created":"2023-06-22","cited_by_count":15,"area":null},{"id":"2104.06669","title":"NAREOR: The Narrative Reordering Problem","created":"2021-04-14","cited_by_count":14,"area":null},{"id":"2502.04577","title":"Position-aware Automatic Circuit Discovery","created":"2025-02-07","cited_by_count":14,"area":"mechinterp"},{"id":"2206.11083","title":"Investigating the Benefits of Free-Form Rationales","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2305.03117","title":"Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2402.14798","title":"Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2305.14770","title":"Using Natural Language Explanations to Rescale Human Judgments","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2602.17053","title":"RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2109.06853","title":"Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension","created":"2021-09-14","cited_by_count":10,"area":null},{"id":"2305.12710","title":"Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture","created":"2023-05-22","cited_by_count":10,"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":"2204.07142","title":"CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations","created":"2022-04-14","cited_by_count":9,"area":null},{"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":"2407.03545","title":"On Evaluating Explanation Utility for Human-AI Decision Making in NLP","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2504.06227","title":"LExT: Towards Evaluating Trustworthiness of Natural Language Explanations","created":"2025-04-08","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":"2312.01582","title":"Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2503.23899","title":"Rubrik's Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2505.24264","title":"Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2210.17095","title":"RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees","created":"2022-10-31","cited_by_count":7,"area":"lr"},{"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":"2401.17824","title":"A Survey of Pre-trained Language Models for Processing Scientific Text","created":"2024-01-31","cited_by_count":7,"area":null},{"id":"2406.13905","title":"Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2109.03756","title":"Diagnostics-Guided Explanation Generation","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2211.07950","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2303.17876","title":"WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset","created":"2023-03-31","cited_by_count":6,"area":null},{"id":"2110.11929","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","created":"2021-10-22","cited_by_count":5,"area":null},{"id":"2209.01061","title":"INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations","created":"2022-09-02","cited_by_count":5,"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":"2305.14237","title":"HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision","created":"2023-05-23","cited_by_count":5,"area":"lr"},{"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":"2311.08614","title":"XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs","created":"2023-11-15","cited_by_count":5,"area":"lr"},{"id":"2402.10767","title":"Inference to the Best Explanation in Large Language Models","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2404.03098","title":"Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2505.24683","title":"Should I Share this Translation? Evaluating Quality Feedback for User Reliance on Machine Translation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2510.16458","title":"Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations","created":"2025-10-18","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":"2410.17099","title":"Human-LLM Hybrid Text Answer Aggregation for Crowd Annotations","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2410.17477","title":"Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2507.00214","title":"Two-Stage Reasoning-Infused Learning: Improving Classification with LLM-Generated Reasoning","created":"2025-06-30","cited_by_count":4,"area":"lr"},{"id":"2510.11210","title":"Discursive Circuits: How Do Language Models Understand Discourse Relations?","created":"2025-10-13","cited_by_count":4,"area":"mechinterp"},{"id":"2111.01663","title":"Classification of Goods Using Text Descriptions With Sentences Retrieval","created":"2021-11-02","cited_by_count":3,"area":null},{"id":"2210.07469","title":"StyLEx: Explaining Style Using Human Lexical Annotations","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2211.08466","title":"Reasoning Circuits: Few-shot Multihop Question Generation with Structured Rationales","created":"2022-11-15","cited_by_count":3,"area":"lr"},{"id":"2212.03747","title":"Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2401.13246","title":"SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning","created":"2024-01-24","cited_by_count":3,"area":"lr"},{"id":"2402.13006","title":"Investigating the Impact of Model Instability on Explanations and Uncertainty","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2501.16382","title":"GraPPI: A Retrieve-Divide-Solve GraphRAG Framework for Large-scale Protein-protein Interaction Exploration","created":"2025-01-24","cited_by_count":3,"area":"rag"},{"id":"2507.01802","title":"The Anatomy of Evidence: An Investigation Into Explainable ICD Coding","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2305.02474","title":"MLHOps: Machine Learning for Healthcare Operations","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2305.13235","title":"SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2310.18496","title":"How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2311.07556","title":"Using Natural Language Explanations to Improve Robustness of In-context Learning","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2403.00662","title":"Modeling the Quality of Dialogical Explanations","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2510.08091","title":"Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2111.00539","title":"Template Filling for Controllable Commonsense Reasoning","created":"2021-10-31","cited_by_count":1,"area":null}],"next_cursor":"100"}