{"total":340,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626,"area":null},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085,"area":null},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569,"area":null},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564,"area":null},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446,"area":null},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415,"area":null},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408,"area":null},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318,"area":null},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307,"area":null},{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302,"area":null},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274,"area":null},{"id":"2406.07496","title":"TextGrad: Automatic \"Differentiation\" via Text","created":"2024-06-11","cited_by_count":273,"area":null},{"id":"2402.14762","title":"MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues","created":"2024-02-22","cited_by_count":250,"area":null},{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243,"area":null},{"id":"2307.11088","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","created":"2023-07-20","cited_by_count":233,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"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":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201,"area":null},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169,"area":null},{"id":"2402.09739","title":"QuRating: Selecting High-Quality Data for Training Language Models","created":"2024-02-15","cited_by_count":157,"area":null},{"id":"2308.11730","title":"Knowledge Graph Prompting for Multi-Document Question Answering","created":"2023-08-22","cited_by_count":152,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2311.09528","title":"HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM","created":"2023-11-16","cited_by_count":142,"area":null},{"id":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138,"area":null},{"id":"2310.00785","title":"BooookScore: A systematic exploration of book-length summarization in the era of LLMs","created":"2023-10-01","cited_by_count":137,"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":"2401.03601","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","created":"2024-01-07","cited_by_count":135,"area":null},{"id":"2412.04261","title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier","created":"2024-12-05","cited_by_count":129,"area":null},{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129,"area":null},{"id":"2405.15032","title":"Aya 23: Open Weight Releases to Further Multilingual Progress","created":"2024-05-23","cited_by_count":123,"area":null},{"id":"2310.20410","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","created":"2023-10-31","cited_by_count":117,"area":null},{"id":"2307.02762","title":"PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations","created":"2023-07-06","cited_by_count":114,"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":"2310.15123","title":"Branch-Solve-Merge Improves Large Language Model Evaluation and Generation","created":"2023-10-23","cited_by_count":106,"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":"2310.05914","title":"NEFTune: Noisy Embeddings Improve Instruction Finetuning","created":"2023-10-09","cited_by_count":100,"area":null},{"id":"2310.11501","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","created":"2023-10-17","cited_by_count":97,"area":null},{"id":"2407.06551","title":"OffsetBias: Leveraging Debiased Data for Tuning Evaluators","created":"2024-07-09","cited_by_count":94,"area":null},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2401.08565","title":"Tuning Language Models by Proxy","created":"2024-01-16","cited_by_count":89,"area":null},{"id":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85,"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":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2402.18667","title":"FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability","created":"2024-02-28","cited_by_count":80,"area":null},{"id":"2405.20253","title":"Evaluating Large Language Model Biases in Persona-Steered Generation","created":"2024-05-30","cited_by_count":78,"area":null},{"id":"2310.18313","title":"FP8-LM: Training FP8 Large Language Models","created":"2023-10-27","cited_by_count":77,"area":null},{"id":"2311.14736","title":"Data Diversity Matters for Robust Instruction Tuning","created":"2023-11-21","cited_by_count":76,"area":null},{"id":"2309.13633","title":"EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria","created":"2023-09-24","cited_by_count":74,"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":"2401.01854","title":"Multilingual Instruction Tuning With Just a Pinch of Multilinguality","created":"2024-01-03","cited_by_count":73,"area":null},{"id":"2309.09150","title":"Can Large Language Models Understand Real-World Complex Instructions?","created":"2023-09-17","cited_by_count":69,"area":null},{"id":"2311.09184","title":"Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization","created":"2023-11-15","cited_by_count":69,"area":null},{"id":"2408.01122","title":"CFBench: A Comprehensive Constraints-Following Benchmark for LLMs","created":"2024-08-02","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":"2308.15022","title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models","created":"2023-08-29","cited_by_count":62,"area":null},{"id":"2310.12962","title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models","created":"2023-10-19","cited_by_count":61,"area":null},{"id":"2401.12087","title":"Revisiting Demonstration Selection Strategies in In-Context Learning","created":"2024-01-22","cited_by_count":58,"area":null},{"id":"2402.10110","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","created":"2024-02-15","cited_by_count":57,"area":null},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2309.13308","title":"Calibrating LLM-Based Evaluator","created":"2023-09-23","cited_by_count":53,"area":null},{"id":"2312.02974","title":"Describing Differences in Image Sets with Natural Language","created":"2023-12-05","cited_by_count":53,"area":null},{"id":"2402.18191","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","created":"2024-02-28","cited_by_count":53,"area":null},{"id":"2502.08745","title":"IHEval: Evaluating Language Models on Following the Instruction Hierarchy","created":"2025-02-12","cited_by_count":53,"area":null},{"id":"2310.05177","title":"Do Large Language Models Know about Facts?","created":"2023-10-08","cited_by_count":51,"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":"2308.01240","title":"Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation","created":"2023-08-02","cited_by_count":50,"area":null},{"id":"2404.03602","title":"Evaluating LLMs at Detecting Errors in LLM Responses","created":"2024-04-04","cited_by_count":50,"area":null},{"id":"2407.01085","title":"Explaining Length Bias in LLM-Based Preference Evaluations","created":"2024-07-01","cited_by_count":49,"area":null},{"id":"2408.10914","title":"To Code, or Not To Code? Exploring Impact of Code in Pre-training","created":"2024-08-20","cited_by_count":47,"area":null},{"id":"2406.17744","title":"Following Length Constraints in Instructions","created":"2024-06-25","cited_by_count":46,"area":null},{"id":"2307.08072","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","created":"2023-07-16","cited_by_count":43,"area":null},{"id":"2404.00725","title":"The Larger the Better? Improved LLM Code-Generation via Budget Reallocation","created":"2024-03-31","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":"2312.12683","title":"Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?","created":"2023-12-20","cited_by_count":39,"area":null},{"id":"2503.05142","title":"RocketEval: Efficient Automated LLM Evaluation via Grading Checklist","created":"2025-03-07","cited_by_count":39,"area":null},{"id":"2308.10032","title":"GameEval: Evaluating LLMs on Conversational Games","created":"2023-08-19","cited_by_count":37,"area":null},{"id":"2402.02101","title":"Are Large Language Models Good Prompt Optimizers?","created":"2024-02-03","cited_by_count":37,"area":null},{"id":"2310.16040","title":"Instruct and Extract: Instruction Tuning for On-Demand Information Extraction","created":"2023-10-24","cited_by_count":36,"area":null},{"id":"2402.15043","title":"KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models","created":"2024-02-23","cited_by_count":36,"area":null},{"id":"2401.12491","title":"Assessing and Understanding Creativity in Large Language Models","created":"2024-01-23","cited_by_count":35,"area":null},{"id":"2310.08367","title":"MCU: An Evaluation Framework for Open-Ended Game Agents","created":"2023-10-12","cited_by_count":34,"area":null},{"id":"2402.10614","title":"Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements","created":"2024-02-16","cited_by_count":34,"area":null},{"id":"2402.16705","title":"SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection","created":"2024-02-26","cited_by_count":34,"area":null},{"id":"2503.04176","title":"TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records","created":"2025-03-06","cited_by_count":34,"area":null},{"id":"2504.07114","title":"ChatBench: From Static Benchmarks to Human-AI Evaluation","created":"2025-03-22","cited_by_count":34,"area":null},{"id":"2402.14334","title":"INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models","created":"2024-02-22","cited_by_count":33,"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":"2402.11889","title":"ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding","created":"2024-02-19","cited_by_count":32,"area":null},{"id":"2406.13439","title":"Finding Blind Spots in Evaluator LLMs with Interpretable Checklists","created":"2024-06-19","cited_by_count":32,"area":null},{"id":"2310.06827","title":"Teaching Language Models to Hallucinate Less with Synthetic Tasks","created":"2023-10-10","cited_by_count":31,"area":null},{"id":"2310.10195","title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate","created":"2023-10-16","cited_by_count":31,"area":null},{"id":"2506.02592","title":"Beyond the Surface: Measuring Self-Preference in LLM Judgments","created":"2025-06-03","cited_by_count":31,"area":null}],"next_cursor":"100"}