{"total":179,"rows":[{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368,"area":null},{"id":"2406.04770","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild","created":"2024-06-07","cited_by_count":218,"area":null},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2407.10457","title":"The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism","created":"2024-07-15","cited_by_count":116,"area":null},{"id":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86,"area":null},{"id":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84,"area":null},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72,"area":null},{"id":"2406.03949","title":"UltraMedical: Building Specialized Generalists in Biomedicine","created":"2024-06-06","cited_by_count":67,"area":null},{"id":"2409.15254","title":"Archon: An Architecture Search Framework for Inference-Time Techniques","created":"2024-09-23","cited_by_count":60,"area":null},{"id":"2506.03136","title":"Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning","created":"2025-06-03","cited_by_count":56,"area":null},{"id":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","cited_by_count":55,"area":null},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2412.04862","title":"EXAONE 3.5: Series of Large Language Models for Real-world Use Cases","created":"2024-12-06","cited_by_count":53,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2410.07137","title":"Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates","created":"2024-10-09","cited_by_count":45,"area":null},{"id":"2509.05830","title":"Finetuning LLMs for Human Behavior Prediction in Social Science Experiments","created":"2025-09-06","cited_by_count":39,"area":null},{"id":"2410.03115","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","created":"2024-10-04","cited_by_count":36,"area":null},{"id":"2506.06303","title":"Reward Is Enough: LLMs Are In-Context Reinforcement Learners","created":"2025-05-21","cited_by_count":31,"area":null},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29,"area":null},{"id":"2501.06521","title":"Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering","created":"2025-01-11","cited_by_count":28,"area":null},{"id":"2507.06187","title":"The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains","created":"2025-07-08","cited_by_count":28,"area":null},{"id":"2508.09303","title":"ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning","created":"2025-08-12","cited_by_count":26,"area":null},{"id":"2502.10645","title":"BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop","created":"2025-02-15","cited_by_count":24,"area":null},{"id":"2406.11683","title":"HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2504.05747","title":"SEA-LION: Southeast Asian Languages in One Network","created":"2025-04-08","cited_by_count":22,"area":null},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2501.00555","title":"Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction","created":"2024-12-31","cited_by_count":18,"area":null},{"id":"2502.12982","title":"Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2502.04498","title":"Verifiable Format Control for Large Language Model Generations","created":"2025-02-06","cited_by_count":17,"area":null},{"id":"2511.09148","title":"LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls","created":"2025-11-12","cited_by_count":17,"area":null},{"id":"2407.15286","title":"Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis","created":"2024-07-21","cited_by_count":15,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2501.12689","title":"IC-Cache: Efficient Large Language Model Serving via In-context Caching","created":"2025-01-22","cited_by_count":13,"area":null},{"id":"2501.18578","title":"R.I.P.: Better Models by Survival of the Fittest Prompts","created":"2025-01-30","cited_by_count":13,"area":null},{"id":"2602.20092","title":"BabyLM Turns 4 and Goes Multilingual: Call for Papers for the 2026 BabyLM Workshop","created":"2026-02-23","cited_by_count":13,"area":null},{"id":"2502.11541","title":"MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2505.14577","title":"TRATES: Trait-Specific Rubric-Assisted Cross-Prompt Essay Scoring","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2512.10551","title":"LLM-Auction: Generative Auction towards LLM-Native Advertising","created":"2025-12-11","cited_by_count":12,"area":null},{"id":"2410.24175","title":"Constraint Back-translation Improves Complex Instruction Following of Large Language Models","created":"2024-10-31","cited_by_count":11,"area":null},{"id":"2509.16591","title":"Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature","created":"2025-09-20","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":"2406.17969","title":"Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective","created":"2024-06-25","cited_by_count":10,"area":null},{"id":"2409.06820","title":"PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation","created":"2024-09-10","cited_by_count":10,"area":null},{"id":"2409.15186","title":"Location is Key: Leveraging Large Language Model for Functional Bug Localization in Verilog","created":"2024-09-23","cited_by_count":10,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2412.00631","title":"ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning","created":"2024-12-01","cited_by_count":10,"area":null},{"id":"2506.13827","title":"Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing","created":"2025-06-15","cited_by_count":10,"area":null},{"id":"2509.21826","title":"ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models","created":"2025-09-26","cited_by_count":10,"area":null},{"id":"2410.13117","title":"Preference Diffusion for Recommendation","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2410.20749","title":"Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs","created":"2024-10-28","cited_by_count":9,"area":null},{"id":"2508.18914","title":"FormaRL: Enhancing Autoformalization with no Labeled Data","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2410.11182","title":"A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2504.00623","title":"Efficient Construction of Model Family through Progressive Training Using Model Expansion","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2505.04066","title":"LLAMAPIE: Proactive In-Ear Conversation Assistants","created":"2025-05-07","cited_by_count":8,"area":null},{"id":"2506.09428","title":"Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting","created":"2025-06-11","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":"2407.10804","title":"Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2409.14672","title":"Speechworthy Instruction-tuned Language Models","created":"2024-09-23","cited_by_count":7,"area":null},{"id":"2411.00412","title":"Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2412.20984","title":"Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2501.09766","title":"iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use","created":"2025-01-15","cited_by_count":7,"area":null},{"id":"2502.16770","title":"LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2505.22990","title":"MenTeR: A fully-automated Multi-agenT workflow for end-to-end RF/Analog Circuits Netlist Design","created":"2025-05-29","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":"2602.22732","title":"Generative Recommendation for Large-Scale Advertising","created":"2026-02-26","cited_by_count":7,"area":null},{"id":"2603.16848","title":"Mediocrity is the key for LLM as a Judge Anchor Selection","created":"2026-03-17","cited_by_count":7,"area":null},{"id":"2605.23912","title":"Raon-Speech Technical Report","created":"2026-04-08","cited_by_count":7,"area":null},{"id":"2408.16493","title":"Learning from Negative Samples in Biomedical Generative Entity Linking","created":"2024-08-29","cited_by_count":6,"area":null},{"id":"2412.17018","title":"GAS: Generative Auto-bidding with Post-training Search","created":"2024-12-22","cited_by_count":6,"area":null},{"id":"2502.02810","title":"Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2506.00297","title":"Improving Protein Sequence Design through Designability Preference Optimization","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2507.22853","title":"Repair-R1: Better Test Before Repair","created":"2025-07-30","cited_by_count":6,"area":null},{"id":"2510.17881","title":"POPI: Personalizing LLMs via Optimized Natural Language Preference Inference","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","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":"2604.27924","title":"Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future","created":"2026-04-30","cited_by_count":6,"area":null},{"id":"2409.02718","title":"\"Yes, My LoRD.\" Guiding Language Model Extraction with Locality Reinforced Distillation","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2410.09543","title":"Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2412.09203","title":"CleanComedy: Creating Friendly Humor through Generative Techniques","created":"2024-12-12","cited_by_count":5,"area":null},{"id":"2501.15007","title":"Controllable Protein Sequence Generation with LLM Preference Optimization","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2509.25837","title":"Distillation of Large Language Models via Concrete Score Matching","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2510.10009","title":"Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learning","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2601.05187","title":"SimuAgent: An LLM-Based Simulink Modeling Assistant Enhanced with Reinforcement Learning","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2602.06181","title":"Investigating Social Bias Changes in Quantized Language Models","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2606.03994","title":"SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2412.03527","title":"FANAL -- Financial Activity News Alerting Language Modeling Framework","created":"2024-12-04","cited_by_count":4,"area":null},{"id":"2506.13674","title":"PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2508.04329","title":"Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2508.16771","title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2601.03534","title":"Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach","created":"2026-01-07","cited_by_count":4,"area":null},{"id":"2604.08553","title":"GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback","created":"2026-03-11","cited_by_count":4,"area":null},{"id":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","cited_by_count":4,"area":null}],"next_cursor":"100"}