{"total":324,"rows":[{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500,"area":null},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262,"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":"2410.12405","title":"ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs","created":"2024-10-16","cited_by_count":149,"area":null},{"id":"2406.11704","title":"Nemotron-4 340B Technical Report","created":"2024-06-17","cited_by_count":144,"area":null},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"area":null},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"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":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105,"area":null},{"id":"2406.09044","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","created":"2024-06-13","cited_by_count":94,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2406.06565","title":"MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures","created":"2024-06-03","cited_by_count":74,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2405.19327","title":"MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series","created":"2024-05-29","cited_by_count":67,"area":null},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64,"area":null},{"id":"2503.08099","title":"Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors","created":"2025-03-11","cited_by_count":62,"area":null},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54,"area":null},{"id":"2412.01708","title":"Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review","created":"2024-12-02","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":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51,"area":null},{"id":"2509.00496","title":"ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics","created":"2025-08-30","cited_by_count":49,"area":null},{"id":"2410.02223","title":"EmbedLLM: Learning Compact Representations of Large Language Models","created":"2024-10-03","cited_by_count":48,"area":null},{"id":"2406.17744","title":"Following Length Constraints in Instructions","created":"2024-06-25","cited_by_count":46,"area":null},{"id":"2510.07284","title":"Online Rubrics Elicitation from Pairwise Comparisons","created":"2025-10-08","cited_by_count":46,"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":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44,"area":null},{"id":"2409.16191","title":"HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models","created":"2024-09-24","cited_by_count":44,"area":null},{"id":"2506.12479","title":"AI Flow: Perspectives, Scenarios, and Approaches","created":"2025-06-14","cited_by_count":44,"area":null},{"id":"2505.18949","title":"The Price of Format: Diversity Collapse in LLMs","created":"2025-05-25","cited_by_count":43,"area":null},{"id":"2410.16256","title":"CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution","created":"2024-10-21","cited_by_count":42,"area":null},{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2412.13091","title":"LMUnit: Fine-grained Evaluation with Natural Language Unit Tests","created":"2024-12-17","cited_by_count":33,"area":null},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31,"area":null},{"id":"2504.15521","title":"The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks","created":"2025-04-22","cited_by_count":31,"area":null},{"id":"2408.08808","title":"Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge","created":"2024-08-16","cited_by_count":30,"area":null},{"id":"2412.09569","title":"JuStRank: Benchmarking LLM Judges for System Ranking","created":"2024-12-12","cited_by_count":29,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","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":"2606.19544","title":"Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias","created":"2026-06-17","cited_by_count":28,"area":null},{"id":"2407.13696","title":"Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBench","created":"2024-07-18","cited_by_count":27,"area":null},{"id":"2407.10627","title":"Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2502.09082","title":"CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation","created":"2025-02-13","cited_by_count":26,"area":null},{"id":"2604.27470","title":"HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats","created":"2026-04-30","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":"2407.21075","title":"Apple Intelligence Foundation Language Models","created":"2024-07-29","cited_by_count":24,"area":null},{"id":"2410.04197","title":"CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints","created":"2024-10-05","cited_by_count":24,"area":null},{"id":"2502.17184","title":"Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric","created":"2025-02-24","cited_by_count":24,"area":null},{"id":"2506.18203","title":"Shrinking the Generation-Verification Gap with Weak Verifiers","created":"2025-06-22","cited_by_count":24,"area":null},{"id":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2410.06040","title":"QERA: an Analytical Framework for Quantization Error Reconstruction","created":"2024-10-08","cited_by_count":22,"area":null},{"id":"2412.03597","title":"The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2408.03541","title":"EXAONE 3.0 7.8B Instruction Tuned Language Model","created":"2024-08-07","cited_by_count":21,"area":null},{"id":"2410.05193","title":"RevisEval: Improving LLM-as-a-Judge via Response-Adapted References","created":"2024-10-07","cited_by_count":20,"area":null},{"id":"2509.21117","title":"TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them","created":"2025-09-25","cited_by_count":20,"area":null},{"id":"2410.02902","title":"Better Instruction-Following Through Minimum Bayes Risk","created":"2024-10-03","cited_by_count":19,"area":null},{"id":"2502.16797","title":"Forecasting Rare Language Model Behaviors","created":"2025-02-24","cited_by_count":19,"area":null},{"id":"2506.13639","title":"An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability","created":"2025-06-16","cited_by_count":19,"area":null},{"id":"2510.00526","title":"Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum","created":"2025-10-01","cited_by_count":18,"area":null},{"id":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"area":null},{"id":"2501.17858","title":"Improving Your Model Ranking on Chatbot Arena by Vote Rigging","created":"2025-01-29","cited_by_count":17,"area":null},{"id":"2502.04688","title":"M-IFEval: Multilingual Instruction-Following Evaluation","created":"2025-02-07","cited_by_count":17,"area":null},{"id":"2506.05984","title":"Audio-Aware Large Language Models as Judges for Speaking Styles","created":"2025-06-06","cited_by_count":17,"area":null},{"id":"2411.07133","title":"Stronger Models are NOT Stronger Teachers for Instruction Tuning","created":"2024-11-11","cited_by_count":16,"area":null},{"id":"2412.05288","title":"StackEval: Benchmarking LLMs in Coding Assistance","created":"2024-11-21","cited_by_count":15,"area":null},{"id":"2507.05727","title":"ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark","created":"2025-07-08","cited_by_count":15,"area":null},{"id":"2509.26072","title":"The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge","created":"2025-09-30","cited_by_count":15,"area":null},{"id":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14,"area":null},{"id":"2410.12869","title":"Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2410.14208","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","created":"2024-10-18","cited_by_count":13,"area":null},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2502.06298","title":"SeaExam and SeaBench: Benchmarking LLMs with Local Multilingual Questions in Southeast Asia","created":"2025-02-10","cited_by_count":13,"area":null},{"id":"2506.01317","title":"T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2506.13342","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","created":"2025-06-16","cited_by_count":13,"area":null},{"id":"2509.25137","title":"The Era of Real-World Human Interaction: RL from User Conversations","created":"2025-09-29","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":"2504.13835","title":"MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space","created":"2025-04-18","cited_by_count":12,"area":null},{"id":"2504.21202","title":"Automatic Legal Writing Evaluation of LLMs","created":"2025-04-29","cited_by_count":12,"area":null},{"id":"2505.13893","title":"InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2507.09104","title":"CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards","created":"2025-07-12","cited_by_count":12,"area":null},{"id":"2408.03092","title":"Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement","created":"2024-08-06","cited_by_count":11,"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":"2411.03743","title":"Automating Exploratory Proteomics Research via Language Models","created":"2024-11-06","cited_by_count":11,"area":null},{"id":"2501.17178","title":"Tuning LLM Judge Design Decisions for 1/1000 of the Cost","created":"2025-01-24","cited_by_count":11,"area":null},{"id":"2503.06573","title":"WildIFEval: Instruction Following in the Wild","created":"2025-03-09","cited_by_count":11,"area":null},{"id":"2505.03814","title":"Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2509.23106","title":"Effective Quantization of Muon Optimizer States","created":"2025-09-27","cited_by_count":11,"area":null},{"id":"2510.18560","title":"WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality","created":"2025-10-21","cited_by_count":11,"area":null},{"id":"2609.27607","title":"Can Jev Judge Radiology Reports? Evaluating a System One Model for Clinical Factuality","created":"2026-09-23","cited_by_count":11,"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":"2409.08706","title":"L3Cube-IndicQuest: A Benchmark Question Answering Dataset for Evaluating Knowledge of LLMs in Indic Context","created":"2024-09-13","cited_by_count":10,"area":null},{"id":"2502.12706","title":"Scalable Model Merging with Progressive Layer-wise Distillation","created":"2025-02-18","cited_by_count":10,"area":null},{"id":"2502.17787","title":"AIR: Complex Instruction Generation via Automatic Iterative Refinement","created":"2025-02-25","cited_by_count":10,"area":null},{"id":"2504.15027","title":"DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models","created":"2025-04-21","cited_by_count":10,"area":null}],"next_cursor":"100"}