{"total":63,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2402.09880","title":"Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence","created":"2024-02-15","cited_by_count":68,"area":null},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2406.14805","title":"How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions","created":"2024-06-21","cited_by_count":52,"area":null},{"id":"2412.10999","title":"Cocoa: Co-Planning and Co-Execution with AI Agents","created":"2024-12-14","cited_by_count":39,"area":null},{"id":"2409.20288","title":"LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models","created":"2024-09-30","cited_by_count":37,"area":null},{"id":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26,"area":"safety"},{"id":"2504.07887","title":"Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge","created":"2025-04-10","cited_by_count":23,"area":"safety"},{"id":"2503.22759","title":"Data Poisoning in Deep Learning: A Survey","created":"2025-03-27","cited_by_count":20,"area":"safety"},{"id":"2402.16142","title":"From Text to Transformation: A Comprehensive Review of Large Language Models' Versatility","created":"2024-02-25","cited_by_count":19,"area":null},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2406.19712","title":"Uncertainty Quantification in Large Language Models Through Convex Hull Analysis","created":"2024-06-28","cited_by_count":13,"area":null},{"id":"2410.07304","title":"The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making","created":"2024-10-09","cited_by_count":12,"area":"alignment"},{"id":"2503.04804","title":"What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2509.08486","title":"Too Helpful, Too Harmless, Too Honest or Just Right?","created":"2025-09-10","cited_by_count":9,"area":"moe"},{"id":"2409.13484","title":"'Since Lawyers are Males..': Examining Implicit Gender Bias in Hindi Language Generation by LLMs","created":"2024-09-20","cited_by_count":8,"area":null},{"id":"2411.10912","title":"SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment","created":"2024-11-16","cited_by_count":6,"area":"alignment"},{"id":"2508.11222","title":"ORFuzz: Fuzzing the \"Other Side\" of LLM Safety -- Testing Over-Refusal","created":"2025-08-15","cited_by_count":6,"area":"safety"},{"id":"2604.19974","title":"Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders","created":"2026-04-21","cited_by_count":6,"area":"mechinterp"},{"id":"2407.06798","title":"It Cannot Be Right If It Was Written by AI: On Lawyers' Preferences of Documents Perceived as Authored by an LLM vs a Human","created":"2024-07-09","cited_by_count":5,"area":null},{"id":"2411.04671","title":"CUIfy the XR: An Open-Source Package to Embed LLM-powered Conversational Agents in XR","created":"2024-11-07","cited_by_count":5,"area":"agents"},{"id":"2412.04498","title":"Large Language Models in Politics and Democracy: A Comprehensive Survey","created":"2024-12-01","cited_by_count":5,"area":null},{"id":"2601.06216","title":"LLM Agents in Law: Taxonomy, Applications, and Challenges","created":"2026-01-08","cited_by_count":5,"area":"agents"},{"id":"2410.23902","title":"Responsible Retrieval Augmented Generation for Climate Decision Making from Documents","created":"2024-10-31","cited_by_count":4,"area":"rag"},{"id":"2506.01386","title":"ThinkEval: Practical Evaluation of Knowledge Leakage in LLM Editing using Thought-based Knowledge Graphs","created":"2025-06-02","cited_by_count":4,"area":"lr"},{"id":"2506.14200","title":"ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2602.18916","title":"Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoning","created":"2026-02-21","cited_by_count":4,"area":"lr"},{"id":"2409.01087","title":"Pre-Trained Language Models for Keyphrase Prediction: A Review","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2505.18575","title":"Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2508.00673","title":"MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2509.07925","title":"GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2509.17044","title":"AgriDoctor: A Multimodal Intelligent Assistant for Agriculture","created":"2025-09-21","cited_by_count":3,"area":null},{"id":"2504.17723","title":"Statistical Runtime Verification for LLMs via Robustness Estimation","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2506.17881","title":"GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication","created":"2025-06-22","cited_by_count":2,"area":"safety"},{"id":"2510.15345","title":"Readability Reconsidered: A Cross-Dataset Analysis of Reference-Free Metrics","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2512.19570","title":"The Epistemological Consequences of Large Language Models: Rethinking collective intelligence and institutional knowledge","created":"2025-12-22","cited_by_count":2,"area":"lr"},{"id":"2602.03775","title":"An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agents","created":"2026-02-03","cited_by_count":2,"area":"agents"},{"id":"2410.05305","title":"Output Scouting: Auditing Large Language Models for Catastrophic Responses","created":"2024-10-04","cited_by_count":1,"area":"safety"},{"id":"2503.12923","title":"Lifelong Reinforcement Learning with Similarity-Driven Weighting by Large Models","created":"2025-03-17","cited_by_count":1,"area":"deeprl"},{"id":"2504.14044","title":"Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models: A Railway Casestudy","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2505.13766","title":"A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2506.23107","title":"Can Large Language Models Capture Human Risk Preferences? A Cross-Cultural Study","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2509.16400","title":"'Rich Dad, Poor Lad': How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2602.04456","title":"Growth First, Care Second? Tracing the Landscape of LLM Value Preferences in Everyday Dilemmas","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.07381","title":"When the Model Said 'No Comment', We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified","created":"2026-02-07","cited_by_count":1,"area":"moe"},{"id":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2508.12727","title":"FedSODA: Federated Fine-tuning of LLMs via Similarity Group Pruning and Orchestrated Distillation Alignment","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2509.19680","title":"PolicyPad: Collaborative Prototyping of LLM Policies","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.01638","title":"Towards Human-Centered RegTech: Unpacking Professionals' Strategies and Needs for Using LLMs Safely","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.03771","title":"OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation","created":"2025-10-04","cited_by_count":0,"area":"agents"},{"id":"2512.04131","title":"Artificial Intelligence / Human Intelligence: Who Controls Whom?","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.12869","title":"ERA-IT: Aligning Semantic Models with Revealed Economic Preference for Real-Time and Explainable Patent Valuation","created":"2025-12-14","cited_by_count":0,"area":"alignment"},{"id":"2603.11001","title":"RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.17260","title":"Rethinking Meeting Effectiveness: A Benchmark and Framework for Temporal Fine-grained Automatic Meeting Effectiveness Evaluation","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.02765","title":"U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.09492","title":"APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.12890","title":"Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts","created":"2026-05-13","cited_by_count":0,"area":"mechinterp"},{"id":"2606.28538","title":"Legal Domain Adaptation of Modern BERT Models","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.23888","title":"Visible to the Court: How AI Is (and Isn't) Litigated in U.S. Federal Court Opinions","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2607.25057","title":"Psychological Influences of Conversational AI: Research and Design Directions for Reducing Harm and Promoting Well-Being","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2610.01282","title":"Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02877","title":"Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging Difficulty","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}