{"list":"other","total":64,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2602.15763","title":"GLM-5: from Vibe Coding to Agentic Engineering","created":"2026-02-17","cited_by_count":587},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2004.07667","title":"Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection","created":"2020-04-16","cited_by_count":455},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2507.21509","title":"Persona Vectors: Monitoring and Controlling Character Traits in Language Models","created":"2025-07-29","cited_by_count":345},{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176},{"id":"2312.14852","title":"TACO: Topics in Algorithmic COde generation dataset","created":"2023-12-22","cited_by_count":160},{"id":"2010.05731","title":"Probing Pretrained Language Models for Lexical Semantics","created":"2020-10-12","cited_by_count":156},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101},{"id":"2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","created":"2025-10-15","cited_by_count":101},{"id":"2409.15647","title":"Looped Transformers for Length Generalization","created":"2024-09-24","cited_by_count":99},{"id":"2511.22570","title":"DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning","created":"2025-11-27","cited_by_count":94},{"id":"2505.16552","title":"Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains","created":"2025-05-22","cited_by_count":85},{"id":"2503.10965","title":"Auditing language models for hidden objectives","created":"2025-03-14","cited_by_count":83},{"id":"2504.05185","title":"Concise Reasoning via Reinforcement Learning","created":"2025-04-07","cited_by_count":79},{"id":"2510.20270","title":"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases","created":"2025-10-23","cited_by_count":65},{"id":"2506.10910","title":"Magistral","created":"2025-06-12","cited_by_count":60},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58},{"id":"2512.18311","title":"Monitoring Monitorability","created":"2025-12-20","cited_by_count":58},{"id":"2502.13295","title":"Demonstrating specification gaming in reasoning models","created":"2025-02-18","cited_by_count":56},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56},{"id":"2505.23575","title":"CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring","created":"2025-05-29","cited_by_count":54},{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53},{"id":"2607.07946","title":"DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks","created":"2026-07-08","cited_by_count":49},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41},{"id":"2601.04603","title":"Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks","created":"2026-01-08","cited_by_count":41},{"id":"2603.05488","title":"Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought","created":"2026-03-05","cited_by_count":40},{"id":"2508.03346","title":"Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy","created":"2025-08-05","cited_by_count":38},{"id":"2602.11964","title":"Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments","created":"2026-02-12","cited_by_count":33},{"id":"2505.14617","title":"The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness","created":"2025-05-20","cited_by_count":30},{"id":"2508.04266","title":"ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents","created":"2025-08-06","cited_by_count":28},{"id":"2511.20703","title":"PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach","created":"2025-11-24","cited_by_count":22},{"id":"2604.17596","title":"Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories","created":"2026-04-19","cited_by_count":15},{"id":"2511.11584","title":"Output Supervision Can Obfuscate the Chain of Thought","created":"2025-10-11","cited_by_count":13},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4},{"id":"2606.06223","title":"From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents","created":"2026-06-04","cited_by_count":3},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2},{"id":"2606.24251","title":"Probing the Misaligned Thinking Process of Language Models","created":"2026-06-23","cited_by_count":1}],"next_cursor":null}