{"total":169,"rows":[{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259,"area":null},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2311.07590","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","created":"2023-11-09","cited_by_count":146,"area":null},{"id":"2402.14903","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","created":"2024-02-22","cited_by_count":115,"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":"2405.20974","title":"SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales","created":"2024-05-31","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":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2309.15840","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","created":"2023-09-26","cited_by_count":83,"area":null},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71,"area":null},{"id":"2401.11624","title":"In-context Learning with Retrieved Demonstrations for Language Models: A Survey","created":"2024-01-21","cited_by_count":70,"area":null},{"id":"2410.03768","title":"Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs","created":"2024-10-02","cited_by_count":55,"area":null},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2504.00125","title":"LLMs for Explainable AI: A Comprehensive Survey","created":"2025-03-31","cited_by_count":45,"area":null},{"id":"2504.14150","title":"Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations","created":"2025-04-19","cited_by_count":45,"area":null},{"id":"2604.02029","title":"The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook","created":"2026-04-02","cited_by_count":43,"area":null},{"id":"2401.07950","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","created":"2024-01-15","cited_by_count":39,"area":null},{"id":"2405.01576","title":"Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant","created":"2024-04-25","cited_by_count":38,"area":null},{"id":"2311.03533","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models","created":"2023-11-06","cited_by_count":32,"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":"2505.18889","title":"Security Concerns for Large Language Models: A Survey","created":"2025-05-24","cited_by_count":29,"area":null},{"id":"2602.15785","title":"This human study did not involve human subjects: Validating LLM simulations as behavioral evidence","created":"2026-02-17","cited_by_count":29,"area":null},{"id":"2401.13986","title":"Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning","created":"2024-01-25","cited_by_count":26,"area":null},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2311.08576","title":"Towards Evaluating AI Systems for Moral Status Using Self-Reports","created":"2023-11-14","cited_by_count":22,"area":null},{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"area":null},{"id":"2403.07794","title":"Fine-tuning Large Language Models with Sequential Instructions","created":"2024-03-12","cited_by_count":20,"area":null},{"id":"2402.04678","title":"FaithLM: Towards Faithful Explanations for Large Language Models","created":"2024-02-07","cited_by_count":19,"area":null},{"id":"2605.19943","title":"Probabilistic Tiny Recursive Model","created":"2026-05-19","cited_by_count":19,"area":null},{"id":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2412.18004","title":"Correctness is not Faithfulness in RAG Attributions","created":"2024-12-23","cited_by_count":18,"area":null},{"id":"2507.19218","title":"Technological folie \\`a deux: Feedback Loops Between AI Chatbots and Mental Illness","created":"2025-07-25","cited_by_count":15,"area":null},{"id":"2310.17639","title":"In-Context Learning Dynamics with Random Binary Sequences","created":"2023-10-26","cited_by_count":13,"area":null},{"id":"2504.13752","title":"Learning to Attribute with Attention","created":"2025-04-18","cited_by_count":13,"area":null},{"id":"2502.18848","title":"A Causal Lens for Evaluating Faithfulness Metrics","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2512.15712","title":"Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants","created":"2025-12-17","cited_by_count":12,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2309.16573","title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2502.18156","title":"Can LLMs Explain Themselves Counterfactually?","created":"2025-02-25","cited_by_count":10,"area":null},{"id":"2505.21024","title":"Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2507.04491","title":"A validity-guided workflow for robust large language model research in psychology","created":"2025-07-06","cited_by_count":8,"area":null},{"id":"2602.23163","title":"A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2410.15489","title":"Generative AI Agents in Autonomous Machines: A Safety Perspective","created":"2024-10-20","cited_by_count":7,"area":null},{"id":"2406.16203","title":"LLMs' Classification Performance is Overclaimed","created":"2024-06-23","cited_by_count":6,"area":null},{"id":"2504.19622","title":"From Evidence to Belief: A Bayesian Epistemology Approach to Language Models","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2601.13717","title":"Simulated Ignorance Fails: A Systematic Study of LLM Behaviors on Forecasting Problems Before Model Knowledge Cutoff","created":"2026-01-20","cited_by_count":6,"area":null},{"id":"2604.09563","title":"Seven simple steps for log analysis in AI systems","created":"2026-02-13","cited_by_count":6,"area":null},{"id":"2401.17703","title":"WSC+: Enhancing The Winograd Schema Challenge Using Tree-of-Experts","created":"2024-01-31","cited_by_count":5,"area":null},{"id":"2410.12284","title":"Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2511.03235","title":"From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers","created":"2025-11-05","cited_by_count":5,"area":null},{"id":"2602.16201","title":"Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2605.01048","title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2311.09613","title":"Digital Socrates: Evaluating LLMs through Explanation Critiques","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2410.13776","title":"Aggregation Artifacts in Subjective Tasks Collapse Large Language Models' Posteriors","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2603.00539","title":"Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement","created":"2026-02-28","cited_by_count":4,"area":null},{"id":"2603.27343","title":"WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking","created":"2026-03-28","cited_by_count":4,"area":null},{"id":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2410.10728","title":"Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2412.12318","title":"Graph-Guided Textual Explanation Generation Framework","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2412.14009","title":"Cognition Chain for Explainable Psychological Stress Detection on Social Media","created":"2024-12-18","cited_by_count":3,"area":null},{"id":"2501.18291","title":"CueTip: An Interactive and Explainable Physics-aware Pool Assistant","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2505.18970","title":"Learning to Explain: Prototype-Based Surrogate Models for LLM Classification","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2508.02584","title":"MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2602.05532","title":"Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2603.07990","title":"MJ1: Multimodal Judgment via Grounded Verification","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2605.01771","title":"The Compliance Gap: Why AI Systems Promise to Follow Process Instructions but Don't","created":"2026-05-03","cited_by_count":3,"area":null},{"id":"2605.23055","title":"Decomposing and Measuring Evaluation Awareness","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.23175","title":"Position: Correct Answer, Wrong Mechanism -- When AI Scientists Defend General Claims Their Own Data Contradicts","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2608.23875","title":"AI Finds A Way","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2311.09558","title":"What if you said that differently?: How Explanation Formats Affect Human Feedback Efficacy and User Perception","created":"2023-11-16","cited_by_count":2,"area":null},{"id":"2403.04770","title":"Social Orientation: A New Feature for Dialogue Analysis","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2505.04528","title":"Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2508.21452","title":"From Canonical to Complex: Benchmarking LLM Capabilities in Undergraduate Thermodynamics","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2604.25922","title":"Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.16407","title":"Proof-Carrying Certificates for LLM Pipelines: A Trust-Boundary Architecture","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2607.25364","title":"Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2504.03640","title":"Bonsai: Interpretable Tree-Adaptive Grounded Reasoning","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2505.08739","title":"Probability Consistency in Large Language Models: Theoretical Foundations Meet Empirical Discrepancies","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2510.08624","title":"Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2512.05765","title":"AGI Requires a Coordination Layer on Top of Pattern Repositories","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2601.04157","title":"FLEx: Language Modeling with Few-shot Language Explanations","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.04369","title":"Generalization to Political Beliefs from Fine-Tuning on Sports Team Preferences","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2602.11448","title":"Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.23546","title":"Humans and LLMs Diverge on Probabilistic Inferences","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.25861","title":"Why Safety Probes Catch Liars But Miss Fanatics","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.08588","title":"Act or Escalate? Evaluating Escalation Behavior in Automation with Language Models","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.19092","title":"Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.05403","title":"Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.21678","title":"Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers","created":"2026-06-19","cited_by_count":1,"area":null}],"next_cursor":"100"}