{"list":"other","total":69,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429},{"id":"2203.10807","title":"ViM: Out-Of-Distribution with Virtual-logit Matching","created":"2022-03-21","cited_by_count":405},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197},{"id":"2501.17399","title":"MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs","created":"2025-01-29","cited_by_count":180},{"id":"2404.12253","title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","created":"2024-04-18","cited_by_count":125},{"id":"2305.15852","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","created":"2023-05-25","cited_by_count":124},{"id":"2210.14707","title":"Is Out-of-Distribution Detection Learnable?","created":"2022-10-26","cited_by_count":109},{"id":"2505.23840","title":"Measuring Sycophancy of Language Models in Multi-turn Dialogues","created":"2025-05-28","cited_by_count":104},{"id":"2410.11414","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","created":"2024-10-15","cited_by_count":101},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99},{"id":"2505.14489","title":"Reasoning Models Better Express Their Confidence","created":"2025-05-20","cited_by_count":65},{"id":"2311.09410","title":"When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour","created":"2023-11-15","cited_by_count":62},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57},{"id":"2403.01548","title":"In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation","created":"2024-03-03","cited_by_count":45},{"id":"2301.07779","title":"Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection","created":"2023-01-18","cited_by_count":44},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44},{"id":"2311.15548","title":"Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination","created":"2023-11-27","cited_by_count":41},{"id":"2502.14565","title":"ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification","created":"2025-02-20","cited_by_count":35},{"id":"2505.12886","title":"Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective","created":"2025-05-19","cited_by_count":34},{"id":"2509.03531","title":"Real-Time Detection of Hallucinated Entities in Long-Form Generation","created":"2025-08-26","cited_by_count":34},{"id":"2507.16488","title":"ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs","created":"2025-07-22","cited_by_count":32},{"id":"2406.12053","title":"InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States","created":"2024-06-17","cited_by_count":30},{"id":"2501.09959","title":"A Survey on Multi-Turn Interaction Capabilities of Large Language Models","created":"2025-01-17","cited_by_count":30},{"id":"2412.19513","title":"Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs","created":"2024-12-27","cited_by_count":29},{"id":"2403.02889","title":"InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers","created":"2024-03-05","cited_by_count":27},{"id":"2508.04826","title":"Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History","created":"2025-08-06","cited_by_count":26},{"id":"2508.08285","title":"The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs","created":"2025-08-01","cited_by_count":22},{"id":"2506.06923","title":"Boosting LLM Reasoning via Spontaneous Self-Correction","created":"2025-06-07","cited_by_count":18},{"id":"2406.02378","title":"On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept","created":"2024-06-04","cited_by_count":16},{"id":"2502.00577","title":"Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach","created":"2025-02-01","cited_by_count":16},{"id":"2311.09603","title":"Self-Contradictory Reasoning Evaluation and Detection","created":"2023-11-16","cited_by_count":14},{"id":"2502.14592","title":"\"Don't Forget the Teachers\": Towards an Educator-Centered Understanding of Harms from Large Language Models in Education","created":"2025-02-20","cited_by_count":14},{"id":"2508.02018","title":"SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models","created":"2025-08-04","cited_by_count":14},{"id":"2311.09182","title":"ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models","created":"2023-11-15","cited_by_count":12},{"id":"2411.04847","title":"Prompt-Guided Internal States for Hallucination Detection of Large Language Models","created":"2024-11-07","cited_by_count":8},{"id":"2411.14842","title":"Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Audio-Language Models","created":"2024-11-22","cited_by_count":7},{"id":"2504.18114","title":"Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection","created":"2025-04-25","cited_by_count":6},{"id":"2409.03381","title":"CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasks","created":"2024-09-05","cited_by_count":5},{"id":"2408.10608","title":"BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models","created":"2024-08-20","cited_by_count":4},{"id":"2409.18205","title":"Bridging OOD Detection and Generalization: A Graph-Theoretic View","created":"2024-09-26","cited_by_count":3},{"id":"2412.08274","title":"2M-BELEBELE: Highly Multilingual Speech and American Sign Language Comprehension Dataset","created":"2024-12-11","cited_by_count":3},{"id":"2511.19155","title":"EEG-VLM: A Hierarchical Vision-Language Model with Multi-Level Feature Alignment and Visually Enhanced Language-Guided Reasoning for EEG Image-Based Sleep Stage Prediction","created":"2025-11-24","cited_by_count":3},{"id":"2507.04237","title":"Structural Classification of Locally Stationary Time Series Based on Second-order Characteristics","created":"2025-07-06","cited_by_count":2}],"next_cursor":null}