{"total":207,"rows":[{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703,"area":"lr"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2307.14539","title":"Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models","created":"2023-07-26","cited_by_count":273,"area":"mllm"},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246,"area":"lr"},{"id":"2311.04076","title":"Do LLMs exhibit human-like response biases? A case study in survey design","created":"2023-11-07","cited_by_count":180,"area":null},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178,"area":null},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2406.13352","title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","created":"2024-06-19","cited_by_count":145,"area":"agents"},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130,"area":"synth"},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2412.16682","title":"The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents","created":"2024-12-21","cited_by_count":99,"area":"agents"},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"area":null},{"id":"2504.08165","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2025-04-10","cited_by_count":88,"area":null},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83,"area":"lr"},{"id":"2310.10638","title":"In-context Pretraining: Language Modeling Beyond Document Boundaries","created":"2023-10-16","cited_by_count":79,"area":null},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2508.14925","title":"MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers","created":"2025-08-19","cited_by_count":66,"area":"agents"},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2312.10523","title":"Paloma: A Benchmark for Evaluating Language Model Fit","created":"2023-12-16","cited_by_count":54,"area":null},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50,"area":null},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50,"area":"lr"},{"id":"2402.04177","title":"Scaling Laws for Downstream Task Performance of Large Language Models","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2308.01404","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","created":"2023-07-05","cited_by_count":47,"area":null},{"id":"2405.14125","title":"ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation","created":"2024-05-23","cited_by_count":47,"area":"agents"},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2406.00755","title":"Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction","created":"2024-06-02","cited_by_count":45,"area":"lr"},{"id":"2310.19677","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","created":"2023-10-30","cited_by_count":44,"area":"alignment"},{"id":"2401.06961","title":"CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities","created":"2024-01-13","cited_by_count":44,"area":"lr"},{"id":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43,"area":"safety"},{"id":"2510.15994","title":"MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents","created":"2025-10-14","cited_by_count":42,"area":"agents"},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2310.09139","title":"The Consensus Game: Language Model Generation via Equilibrium Search","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2404.10830","title":"Fewer Truncations Improve Language Modeling","created":"2024-04-16","cited_by_count":35,"area":null},{"id":"2405.02287","title":"Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models","created":"2024-05-03","cited_by_count":35,"area":"mllm"},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2409.15268","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking","created":"2024-09-23","cited_by_count":35,"area":"alignment"},{"id":"2601.04748","title":"When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail","created":"2026-01-08","cited_by_count":35,"area":"agents"},{"id":"2409.05283","title":"On the Relationship between Truth and Political Bias in Language Models","created":"2024-09-09","cited_by_count":31,"area":"alignment"},{"id":"2507.00885","title":"Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check","created":"2025-07-01","cited_by_count":29,"area":null},{"id":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26,"area":null},{"id":"2403.02419","title":"Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems","created":"2024-03-04","cited_by_count":25,"area":null},{"id":"2406.02575","title":"Cross-Modal Safety Alignment: Is textual unlearning all you need?","created":"2024-05-27","cited_by_count":25,"area":"mllm"},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2310.09753","title":"When can transformers reason with abstract symbols?","created":"2023-10-15","cited_by_count":24,"area":null},{"id":"2401.10463","title":"Critical Data Size of Language Models from a Grokking Perspective","created":"2024-01-19","cited_by_count":24,"area":null},{"id":"2404.07234","title":"Goal-guided Generative Prompt Injection Attack on Large Language Models","created":"2024-04-06","cited_by_count":24,"area":"safety"},{"id":"2401.00788","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","created":"2024-01-01","cited_by_count":23,"area":null},{"id":"2406.12158","title":"LLMs Are Prone to Fallacies in Causal Inference","created":"2024-06-18","cited_by_count":23,"area":null},{"id":"2407.10725","title":"CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses","created":"2024-07-15","cited_by_count":23,"area":null},{"id":"2510.16380","title":"MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes","created":"2025-10-18","cited_by_count":23,"area":"lr"},{"id":"2311.07811","title":"In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax","created":"2023-11-13","cited_by_count":22,"area":null},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2410.07074","title":"Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning","created":"2024-10-09","cited_by_count":21,"area":null},{"id":"2311.00445","title":"A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models","created":"2023-11-01","cited_by_count":20,"area":"lr"},{"id":"2503.19622","title":"Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation","created":"2025-03-25","cited_by_count":20,"area":"lr"},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2410.22446","title":"Do Large Language Models Align with Core Mental Health Counseling Competencies?","created":"2024-10-29","cited_by_count":19,"area":null},{"id":"2405.13684","title":"CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models","created":"2024-05-22","cited_by_count":18,"area":null},{"id":"2406.14230","title":"Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2408.11006","title":"Security Attacks on LLM-based Code Completion Tools","created":"2024-08-20","cited_by_count":16,"area":"safety"},{"id":"2506.03149","title":"Causal Estimation of Tokenisation Bias","created":"2025-06-03","cited_by_count":16,"area":null},{"id":"2510.05197","title":"Efficient Prediction of Pass@k Scaling in Large Language Models","created":"2025-10-06","cited_by_count":16,"area":null},{"id":"2309.05217","title":"Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis","created":"2023-09-11","cited_by_count":15,"area":null},{"id":"2402.07896","title":"Suppressing Pink Elephants with Direct Principle Feedback","created":"2024-02-12","cited_by_count":15,"area":"alignment"},{"id":"2405.10799","title":"Training Compute Thresholds: Features and Functions in AI Regulation","created":"2024-05-17","cited_by_count":14,"area":null},{"id":"2410.03857","title":"You Know What I'm Saying: Jailbreak Attack via Implicit Reference","created":"2024-10-04","cited_by_count":14,"area":"safety"},{"id":"2601.07395","title":"MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP","created":"2026-01-12","cited_by_count":14,"area":"agents"},{"id":"2308.04813","title":"CLEVA: Chinese Language Models EVAluation Platform","created":"2023-08-09","cited_by_count":13,"area":null},{"id":"2505.22946","title":"NegVQA: Can Vision Language Models Understand Negation?","created":"2025-05-28","cited_by_count":13,"area":"mllm"},{"id":"2510.24963","title":"Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale","created":"2025-10-28","cited_by_count":13,"area":null},{"id":"2601.13770","title":"Look-Ahead-Bench: a Standardized Benchmark of Look-ahead Bias in Point-in-Time LLMs for Finance","created":"2026-01-20","cited_by_count":13,"area":null},{"id":"2503.03862","title":"Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2403.03419","title":"Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization","created":"2024-03-06","cited_by_count":11,"area":"alignment"},{"id":"2406.17295","title":"Less can be more for predicting properties with large language models","created":"2024-06-25","cited_by_count":11,"area":null},{"id":"2502.01349","title":"Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations","created":"2025-02-03","cited_by_count":11,"area":null},{"id":"2505.14172","title":"The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models","created":"2025-05-20","cited_by_count":11,"area":null},{"id":"2506.10979","title":"How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?","created":"2025-06-12","cited_by_count":11,"area":"lr"},{"id":"2508.12461","title":"Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models","created":"2025-08-17","cited_by_count":11,"area":"moe"},{"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":"2410.01692","title":"U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2410.10796","title":"Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2502.19190","title":"Provocations from the Humanities for Generative AI Research","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2310.05163","title":"An Investigation of LLMs' Inefficacy in Understanding Converse Relations","created":"2023-10-08","cited_by_count":9,"area":null},{"id":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2312.07779","title":"Tell, don't show: Declarative facts influence how LLMs generalize","created":"2023-12-12","cited_by_count":9,"area":null},{"id":"2311.07723","title":"Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains","created":"2023-11-13","cited_by_count":8,"area":"alignment"},{"id":"2402.11005","title":"A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive","created":"2024-02-16","cited_by_count":8,"area":null},{"id":"2408.13987","title":"Focused Large Language Models are Stable Many-Shot Learners","created":"2024-08-26","cited_by_count":8,"area":null},{"id":"2507.21476","title":"Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench","created":"2025-07-29","cited_by_count":8,"area":"lr"},{"id":"2406.11353","title":"$\\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts","created":"2024-06-17","cited_by_count":7,"area":"moe"},{"id":"2406.16069","title":"FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models","created":"2024-06-23","cited_by_count":7,"area":null},{"id":"2412.11979","title":"AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2507.06323","title":"Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms","created":"2025-07-08","cited_by_count":7,"area":"agents"},{"id":"2307.03762","title":"Brain in a Vat: On Missing Pieces Towards Artificial General Intelligence in Large Language Models","created":"2023-07-07","cited_by_count":6,"area":null}],"next_cursor":"100"}