{"total":257,"rows":[{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040,"area":null},{"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":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631,"area":null},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177,"area":null},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"area":null},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97,"area":null},{"id":"2306.06283","title":"14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon","created":"2023-06-09","cited_by_count":86,"area":null},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2410.03226","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","created":"2024-10-04","cited_by_count":83,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2302.04012","title":"CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models","created":"2023-02-08","cited_by_count":55,"area":null},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2503.19595","title":"Optimizing Language Models for Inference Time Objectives using Reinforcement Learning","created":"2025-03-25","cited_by_count":53,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48,"area":null},{"id":"2303.03186","title":"Will Affective Computing Emerge from Foundation Models and General AI? A First Evaluation on ChatGPT","created":"2023-03-03","cited_by_count":41,"area":null},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2406.01375","title":"D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models","created":"2024-06-03","cited_by_count":41,"area":null},{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40,"area":null},{"id":"2604.28190","title":"Representation Fr\\'echet Loss for Visual Generation","created":"2026-04-30","cited_by_count":37,"area":null},{"id":"2607.07663","title":"Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops","created":"2026-07-08","cited_by_count":35,"area":null},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2406.15720","title":"Scaling Laws for Fact Memorization of Large Language Models","created":"2024-06-22","cited_by_count":33,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2503.19618","title":"Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data","created":"2025-03-25","cited_by_count":29,"area":null},{"id":"2506.09477","title":"On a few pitfalls in KL divergence gradient estimation for RL","created":"2025-06-11","cited_by_count":29,"area":null},{"id":"2310.03262","title":"Predicting Emergent Abilities with Infinite Resolution Evaluation","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2505.17799","title":"A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances","created":"2025-05-23","cited_by_count":28,"area":null},{"id":"2602.13035","title":"Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL","created":"2026-02-13","cited_by_count":27,"area":null},{"id":"2401.13586","title":"Instruction Fine-Tuning: Does Prompt Loss Matter?","created":"2024-01-24","cited_by_count":26,"area":null},{"id":"2406.04291","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2506.21495","title":"Bridging Offline and Online Reinforcement Learning for LLMs","created":"2025-06-26","cited_by_count":25,"area":null},{"id":"2403.06563","title":"Unraveling the Mystery of Scaling Laws: Part I","created":"2024-03-11","cited_by_count":24,"area":null},{"id":"2506.14261","title":"RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?","created":"2025-06-17","cited_by_count":24,"area":null},{"id":"2401.07301","title":"Small Language Model Can Self-correct","created":"2024-01-14","cited_by_count":23,"area":null},{"id":"2407.17467","title":"CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models","created":"2024-07-24","cited_by_count":23,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2307.08701","title":"AlpaGasus: Training A Better Alpaca with Fewer Data","created":"2023-07-17","cited_by_count":19,"area":null},{"id":"2406.10023","title":"Deep Bayesian Active Learning for Preference Modeling in Large Language Models","created":"2024-06-14","cited_by_count":19,"area":null},{"id":"2506.08473","title":"AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin","created":"2025-06-10","cited_by_count":19,"area":null},{"id":"2602.01601","title":"Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards","created":"2026-02-02","cited_by_count":17,"area":null},{"id":"2409.06446","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","created":"2024-09-10","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":"2510.23393","title":"The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation","created":"2025-10-27","cited_by_count":16,"area":null},{"id":"2302.13137","title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","created":"2023-02-25","cited_by_count":15,"area":null},{"id":"2310.01627","title":"VAL: Interactive Task Learning with GPT Dialog Parsing","created":"2023-10-02","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":"2405.05466","title":"Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals","created":"2024-05-08","cited_by_count":13,"area":null},{"id":"2406.12295","title":"Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding","created":"2024-06-18","cited_by_count":13,"area":null},{"id":"2604.07666","title":"An Imperfect Verifier is Good Enough: Learning with Noisy Rewards","created":"2026-04-09","cited_by_count":13,"area":null},{"id":"2502.19402","title":"General Intelligence Requires Reward-based Pretraining","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2506.01955","title":"Dual-Process Image Generation","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2302.00805","title":"Conditioning Predictive Models: Risks and Strategies","created":"2023-02-02","cited_by_count":11,"area":null},{"id":"2305.13102","title":"Observations on LLMs for Telecom Domain: Capabilities and Limitations","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2503.19612","title":"RL-finetuning LLMs from on- and off-policy data with a single algorithm","created":"2025-03-25","cited_by_count":11,"area":null},{"id":"2602.12222","title":"Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training","created":"2026-02-12","cited_by_count":11,"area":null},{"id":"2607.02375","title":"Representation Distribution Matching for One-Step Visual Generation","created":"2026-07-02","cited_by_count":11,"area":null},{"id":"2506.06987","title":"Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors","created":"2025-06-08","cited_by_count":10,"area":null},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2607.20083","title":"Co-Evolving LLM Evaluators and Policies via DynamicRubric","created":"2026-07-22","cited_by_count":10,"area":null},{"id":"2403.19913","title":"MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models","created":"2024-03-29","cited_by_count":9,"area":null},{"id":"2406.20087","title":"ProgressGym: Alignment with a Millennium of Moral Progress","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2510.03199","title":"Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2603.12520","title":"When LLM Judge Scores Look Good but Best-of-N Decisions Fail","created":"2026-03-12","cited_by_count":9,"area":null},{"id":"2307.10524","title":"Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions","created":"2023-07-20","cited_by_count":8,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2409.17391","title":"Scaling Behavior for Large Language Models regarding Numeral Systems: An Example using Pythia","created":"2024-09-25","cited_by_count":8,"area":null},{"id":"2411.08243","title":"Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset","created":"2024-11-12","cited_by_count":8,"area":null},{"id":"2411.11767","title":"Drowning in Documents: Consequences of Scaling Reranker Inference","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2501.13124","title":"Debate Helps Weak-to-Strong Generalization","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8,"area":null},{"id":"2406.17312","title":"Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2506.19882","title":"Position: Machine Learning Conferences Should Establish a \"Refutations and Critiques\" Track","created":"2025-06-24","cited_by_count":7,"area":null},{"id":"2507.07484","title":"Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models","created":"2025-07-10","cited_by_count":7,"area":null},{"id":"2508.04632","title":"IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2602.07595","title":"TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2602.07729","title":"Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2502.07237","title":"DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2601.19375","title":"Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection","created":"2026-01-27","cited_by_count":6,"area":null},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2607.00871","title":"Self-Evolving Agents with Anytime-Valid Certificates","created":"2026-07-01","cited_by_count":6,"area":null},{"id":"2410.21200","title":"BanglaLlama: LLaMA for Bangla Language","created":"2024-10-28","cited_by_count":5,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null}],"next_cursor":"100"}