{"list":"other","total":71,"rows":[{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"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":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2404.15574","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","created":"2024-04-24","cited_by_count":232},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"2402.00367","title":"Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration","created":"2024-02-01","cited_by_count":180},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159},{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120},{"id":"2411.14257","title":"Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models","created":"2024-11-21","cited_by_count":115},{"id":"2311.09677","title":"R-Tuning: Instructing Large Language Models to Say `I Don't Know'","created":"2023-11-16","cited_by_count":111},{"id":"2410.11414","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","created":"2024-10-15","cited_by_count":101},{"id":"2406.08391","title":"Large Language Models Must Be Taught to Know What They Don't Know","created":"2024-06-12","cited_by_count":100},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99},{"id":"2401.03205","title":"The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models","created":"2024-01-06","cited_by_count":88},{"id":"2312.09230","title":"Successor Heads: Recurring, Interpretable Attention Heads In The Wild","created":"2023-12-14","cited_by_count":77},{"id":"2403.18349","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","created":"2024-03-27","cited_by_count":66},{"id":"2312.03729","title":"Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?","created":"2023-11-27","cited_by_count":62},{"id":"2305.13712","title":"Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models","created":"2023-05-23","cited_by_count":61},{"id":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49},{"id":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44},{"id":"2403.09972","title":"Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection","created":"2024-03-15","cited_by_count":41},{"id":"2403.18167","title":"Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations","created":"2024-03-27","cited_by_count":38},{"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":"2510.13290","title":"To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models","created":"2025-10-15","cited_by_count":29},{"id":"2502.11677","title":"Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception","created":"2025-02-17","cited_by_count":27},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27},{"id":"2403.09037","title":"The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?","created":"2024-03-14","cited_by_count":26},{"id":"2412.06676","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","created":"2024-12-09","cited_by_count":26},{"id":"2505.24362","title":"Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion","created":"2025-05-30","cited_by_count":23},{"id":"2406.07457","title":"Estimating the Hallucination Rate of Generative AI","created":"2024-06-11","cited_by_count":20},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19},{"id":"2509.09708","title":"Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal","created":"2025-09-07","cited_by_count":19},{"id":"2410.07627","title":"Automatic Curriculum Expert Iteration for Reliable LLM Reasoning","created":"2024-10-10","cited_by_count":16},{"id":"2505.13737","title":"Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers","created":"2025-05-19","cited_by_count":16},{"id":"2307.09254","title":"Selective Generation for Controllable Language Models","created":"2023-07-18","cited_by_count":15},{"id":"2508.12495","title":"Mitigating Hallucinations in Large Language Models via Causal Reasoning","created":"2025-08-17","cited_by_count":13},{"id":"2509.22449","title":"Detecting (Un)answerability in Large Language Models with Linear Directions","created":"2025-09-26","cited_by_count":13},{"id":"2601.05679","title":"Do Sparse Autoencoders Identify Reasoning Features in Language Models?","created":"2026-01-09","cited_by_count":12},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11},{"id":"2302.09694","title":"Disentangled Representation for Causal Mediation Analysis","created":"2023-02-19","cited_by_count":10},{"id":"2506.00519","title":"CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention","created":"2025-05-31","cited_by_count":10},{"id":"2510.10390","title":"RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models","created":"2025-10-12","cited_by_count":9},{"id":"2412.12527","title":"When to Speak, When to Abstain: Contrastive Decoding with Abstention","created":"2024-12-17","cited_by_count":8},{"id":"2508.16910","title":"Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment","created":"2025-08-23","cited_by_count":6},{"id":"2504.03579","title":"Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy","created":"2025-04-04","cited_by_count":5},{"id":"2511.17170","title":"Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models","created":"2025-11-21","cited_by_count":5},{"id":"2507.00389","title":"Causal Prompting for Implicit Sentiment Analysis with Large Language Models","created":"2025-07-01","cited_by_count":4},{"id":"2507.20836","title":"First Hallucination Tokens Are Different from Conditional Ones","created":"2025-07-28","cited_by_count":4},{"id":"2511.12991","title":"Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty","created":"2025-11-17","cited_by_count":3},{"id":"2601.08108","title":"Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought","created":"2026-01-13","cited_by_count":2},{"id":"2410.15648","title":"Linking Model Intervention to Causal Interpretation in Model Explanation","created":"2024-10-21","cited_by_count":1},{"id":"2509.23684","title":"Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs","created":"2025-09-28","cited_by_count":1},{"id":"2608.28018","title":"Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning","created":"2026-08-28","cited_by_count":1}],"next_cursor":null}