{"total":76,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396,"area":null},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"id":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194,"area":"lr"},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177,"area":null},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108,"area":"lr"},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"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":"2305.15269","title":"Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples","created":"2023-05-24","cited_by_count":84,"area":"lr"},{"id":"2306.08189","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","created":"2023-06-14","cited_by_count":74,"area":null},{"id":"2305.14235","title":"Multilingual Large Language Models Are Not (Yet) Code-Switchers","created":"2023-05-23","cited_by_count":65,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2310.18168","title":"Personas as a Way to Model Truthfulness in Language Models","created":"2023-10-27","cited_by_count":47,"area":null},{"id":"2402.11655","title":"Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals","created":"2024-02-18","cited_by_count":40,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"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":"2211.07443","title":"Calibrated Interpretation: Confidence Estimation in Semantic Parsing","created":"2022-11-14","cited_by_count":33,"area":null},{"id":"2305.02633","title":"Conformal Nucleus Sampling","created":"2023-05-04","cited_by_count":33,"area":null},{"id":"2307.10558","title":"Instruction-following Evaluation through Verbalizer Manipulation","created":"2023-07-20","cited_by_count":30,"area":null},{"id":"2305.07614","title":"NevIR: Negation in Neural Information Retrieval","created":"2023-05-12","cited_by_count":29,"area":null},{"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":"2401.00788","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","created":"2024-01-01","cited_by_count":23,"area":null},{"id":"2405.10799","title":"Training Compute Thresholds: Features and Functions in AI Regulation","created":"2024-05-17","cited_by_count":14,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","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":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2304.01665","title":"Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks","created":"2023-04-04","cited_by_count":12,"area":"lr"},{"id":"2305.17311","title":"Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models","created":"2023-05-27","cited_by_count":12,"area":null},{"id":"2404.16645","title":"Tele-FLM Technical Report","created":"2024-04-25","cited_by_count":12,"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":"2406.14508","title":"Evidence of a log scaling law for political persuasion with large language models","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2506.03101","title":"Beyond Text Compression: Evaluating Tokenizers Across Scales","created":"2025-06-03","cited_by_count":11,"area":null},{"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":"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":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2601.02316","title":"DatBench: Discriminative, Faithful, and Efficient VLM Evaluations","created":"2026-01-05","cited_by_count":10,"area":null},{"id":"2310.05163","title":"An Investigation of LLMs' Inefficacy in Understanding Converse Relations","created":"2023-10-08","cited_by_count":9,"area":null},{"id":"2502.17356","title":"Random Scaling of Emergent Capabilities","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2306.07384","title":"Probing Quantifier Comprehension in Large Language Models: Another Example of Inverse Scaling","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2504.12562","title":"ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2507.00004","title":"A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search","created":"2025-06-10","cited_by_count":5,"area":"lr"},{"id":"2212.08700","title":"Rarely a problem? Language models exhibit inverse scaling in their predictions following few-type quantifiers","created":"2022-12-16","cited_by_count":4,"area":null},{"id":"2311.09761","title":"MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2402.11349","title":"Language Models Don't Learn the Physical Manifestation of Language","created":"2024-02-17","cited_by_count":4,"area":null},{"id":"2403.09832","title":"Scaling Behavior of Machine Translation with Large Language Models under Prompt Injection Attacks","created":"2024-03-14","cited_by_count":4,"area":"safety"},{"id":"2509.16332","title":"Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2303.13112","title":"A Simple Explanation for the Phase Transition in Large Language Models with List Decoding","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2412.11483","title":"\"They've Stolen My GPL-Licensed Model!\": Toward Standardized and Transparent Model Licensing","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2504.03635","title":"Finding the Minimal Parameter Budget for Implicit Reasoning: A Data Complexity Driven Scaling Law for Language Models","created":"2025-04-04","cited_by_count":3,"area":"lr"},{"id":"2504.06486","title":"Mind the (Data) Gap: Evaluating Vision Systems in Small Data Applications","created":"2025-04-08","cited_by_count":3,"area":null},{"id":"2506.10304","title":"The Alignment Trap: Complexity Barriers","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2512.07665","title":"Reliable agent engineering should integrate machine-compatible organizational principles","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2601.19831","title":"Neural Neural Scaling Laws","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2608.11859","title":"Small-Scale Experiments: Are We There Yet?","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2508.18672","title":"Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2605.29491","title":"The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIF","created":"2026-05-28","cited_by_count":1,"area":"rag"},{"id":"2607.08403","title":"Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2401.17692","title":"Mitigating the Influence of Distractor Tasks in LMs with Prior-Aware Decoding","created":"2024-01-31","cited_by_count":0,"area":null},{"id":"2404.07009","title":"A Mathematical Theory for Learning Semantic Languages by Abstract Learners","created":"2024-04-10","cited_by_count":0,"area":null},{"id":"2410.00699","title":"Investigating the Impact of Model Complexity in Large Language Models","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2602.01227","title":"Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2604.08501","title":"sciwrite-lint: Verification Infrastructure for the Age of Science Vibe-Writing","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.08295","title":"In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot Classification","created":"2026-05-08","cited_by_count":0,"area":"mechinterp"},{"id":"2605.18838","title":"Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.22672","title":"Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2607.16961","title":"Lomekwi: Resource-Bounded Tool Discovery in LLM Agents","created":"2026-07-18","cited_by_count":0,"area":"agents"},{"id":"2608.11741","title":"JieZi: A Large-Scale Expert-Audited Dataset and Benchmark for Ancient Chinese Character Exegesis","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.31118","title":"When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning","created":"2026-08-31","cited_by_count":0,"area":"moe"},{"id":"2609.04373","title":"Why Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial Markets","created":"2026-09-03","cited_by_count":0,"area":"agents"},{"id":"2609.13685","title":"Not all Negation Cues are Equal: Affixal Negations Yield Better Negation Understanding","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}