{"list":"other","total":55,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1905.07697","title":"Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations","created":"2019-05-19","cited_by_count":614},{"id":"2401.06373","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","created":"2024-01-12","cited_by_count":573},{"id":"2306.15626","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","created":"2023-06-27","cited_by_count":427},{"id":"1712.07107","title":"Adversarial Examples: Attacks and Defenses for Deep Learning","created":"2017-12-19","cited_by_count":351},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266},{"id":"2001.02478","title":"Questioning the AI: Informing Design Practices for Explainable AI User Experiences","created":"2020-01-08","cited_by_count":253},{"id":"1903.10464","title":"Explaining individual predictions when features are dependent: More accurate approximations to Shapley values","created":"2019-03-25","cited_by_count":208},{"id":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170},{"id":"2008.05030","title":"Reliable Post hoc Explanations: Modeling Uncertainty in Explainability","created":"2020-08-11","cited_by_count":125},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116},{"id":"1911.06473","title":"\"How do I fool you?\": Manipulating User Trust via Misleading Black Box Explanations","created":"2019-11-15","cited_by_count":111},{"id":"2401.13835","title":"What Large Language Models Know and What People Think They Know","created":"2024-01-24","cited_by_count":110},{"id":"2403.14380","title":"On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial","created":"2024-03-21","cited_by_count":109},{"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},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101},{"id":"2411.15287","title":"Sycophancy in Large Language Models: Causes and Mitigations","created":"2024-11-22","cited_by_count":101},{"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},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83},{"id":"2205.12910","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","created":"2022-05-25","cited_by_count":72},{"id":"2404.05221","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","created":"2024-04-08","cited_by_count":70},{"id":"2304.00008","title":"On the Creativity of Large Language Models","created":"2023-03-27","cited_by_count":57},{"id":"2508.02087","title":"When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models","created":"2025-08-04","cited_by_count":50},{"id":"2312.15523","title":"The Persuasive Power of Large Language Models","created":"2023-12-24","cited_by_count":47},{"id":"2504.00125","title":"LLMs for Explainable AI: A Comprehensive Survey","created":"2025-03-31","cited_by_count":45},{"id":"2504.14150","title":"Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations","created":"2025-04-19","cited_by_count":45},{"id":"2412.15194","title":"MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark","created":"2024-12-19","cited_by_count":41},{"id":"2311.16733","title":"LLMs for Science: Usage for Code Generation and Data Analysis","created":"2023-11-28","cited_by_count":34},{"id":"2405.10632","title":"Towards interactive evaluations for interaction harms in human-AI systems","created":"2024-05-17","cited_by_count":29},{"id":"2302.12832","title":"Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity","created":"2023-02-27","cited_by_count":23},{"id":"2307.02185","title":"Citation: A Key to Building Responsible and Accountable Large Language Models","created":"2023-07-05","cited_by_count":20},{"id":"2402.04678","title":"FaithLM: Towards Faithful Explanations for Large Language Models","created":"2024-02-07","cited_by_count":19},{"id":"2501.01303","title":"Citations and Trust in LLM Generated Responses","created":"2025-01-02","cited_by_count":18},{"id":"2101.09498","title":"Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations","created":"2021-01-23","cited_by_count":15},{"id":"2309.03234","title":"Natural Example-Based Explainability: a Survey","created":"2023-09-05","cited_by_count":13},{"id":"2005.12800","title":"Towards Analogy-Based Explanations in Machine Learning","created":"2020-05-23","cited_by_count":7},{"id":"2302.02944","title":"Learning Complementary Policies for Human-AI Teams","created":"2023-02-06","cited_by_count":7},{"id":"2404.14232","title":"Shifting Focus with HCEye: Exploring the Dynamics of Visual Highlighting and Cognitive Load on User Attention and Saliency Prediction","created":"2024-04-22","cited_by_count":6},{"id":"2406.19170","title":"The Illusion of Competence: Evaluating the Effect of Explanations on Users' Mental Models of Visual Question Answering Systems","created":"2024-06-27","cited_by_count":6},{"id":"2409.15550","title":"Talk, Listen, Connect: How Humans and AI Evaluate Empathy in Responses to Emotionally Charged Narratives","created":"2024-09-23","cited_by_count":6},{"id":"2505.18066","title":"Towards Uncertainty Aware Task Delegation and Human-AI Collaborative Decision-Making","created":"2025-05-23","cited_by_count":4},{"id":"2503.10264","title":"Understanding and Supporting Peer Review Using AI-reframed Positive Summary","created":"2025-03-13","cited_by_count":3},{"id":"2509.21436","title":"Position: Human Factors Reshape Adversarial Analysis in Human-AI Decision-Making Systems","created":"2025-09-25","cited_by_count":1}],"next_cursor":null}