{"total":138,"rows":[{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848,"area":null},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464,"area":null},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2310.17976","title":"InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews","created":"2023-10-27","cited_by_count":179,"area":null},{"id":"2310.15819","title":"Generative Language Models Exhibit Social Identity Biases","created":"2023-10-24","cited_by_count":111,"area":null},{"id":"2311.15653","title":"MoDS: Model-oriented Data Selection for Instruction Tuning","created":"2023-11-27","cited_by_count":107,"area":null},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106,"area":null},{"id":"2401.12474","title":"Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment","created":"2024-01-23","cited_by_count":104,"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":"2410.24190","title":"Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters","created":"2024-10-31","cited_by_count":71,"area":null},{"id":"2402.16153","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","created":"2024-02-25","cited_by_count":68,"area":null},{"id":"2406.10279","title":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","created":"2024-06-12","cited_by_count":65,"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":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2406.19073","title":"AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2406.12585","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","created":"2024-06-18","cited_by_count":33,"area":null},{"id":"2402.11597","title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","created":"2024-02-18","cited_by_count":30,"area":null},{"id":"2406.17681","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","created":"2024-06-25","cited_by_count":29,"area":null},{"id":"2410.03777","title":"Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling","created":"2024-10-03","cited_by_count":28,"area":null},{"id":"2404.02823","title":"Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models","created":"2024-04-03","cited_by_count":27,"area":null},{"id":"2404.15846","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","created":"2024-04-24","cited_by_count":27,"area":null},{"id":"2504.11975","title":"SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes","created":"2025-04-16","cited_by_count":27,"area":null},{"id":"2403.11671","title":"HDLdebugger: Streamlining HDL debugging with Large Language Models","created":"2024-03-18","cited_by_count":26,"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":"2402.16063","title":"Citation-Enhanced Generation for LLM-based Chatbots","created":"2024-02-25","cited_by_count":25,"area":null},{"id":"2404.00566","title":"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks","created":"2024-03-31","cited_by_count":23,"area":null},{"id":"2312.14972","title":"Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production","created":"2023-12-20","cited_by_count":21,"area":null},{"id":"2404.13599","title":"\"A good pun is its own reword\": Can Large Language Models Understand Puns?","created":"2024-04-21","cited_by_count":21,"area":null},{"id":"2312.01678","title":"Jellyfish: A Large Language Model for Data Preprocessing","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2402.18137","title":"DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning","created":"2024-02-28","cited_by_count":20,"area":null},{"id":"2404.04671","title":"PhyloLM : Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks","created":"2024-04-06","cited_by_count":19,"area":null},{"id":"2404.06138","title":"Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages","created":"2024-04-09","cited_by_count":18,"area":null},{"id":"2404.08008","title":"Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition","created":"2024-04-10","cited_by_count":18,"area":null},{"id":"2412.12004","title":"The Open Source Advantage in Large Language Models (LLMs)","created":"2024-12-16","cited_by_count":18,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2406.08903","title":"Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models","created":"2024-06-13","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":"2311.16989","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","created":"2023-11-28","cited_by_count":15,"area":null},{"id":"2405.10659","title":"Realistic Evaluation of Toxicity in Large Language Models","created":"2024-05-17","cited_by_count":15,"area":null},{"id":"2410.18565","title":"Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2411.11081","title":"The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection","created":"2024-11-17","cited_by_count":15,"area":null},{"id":"2501.03545","title":"Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation","created":"2025-01-07","cited_by_count":15,"area":null},{"id":"2505.11329","title":"TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference","created":"2025-05-16","cited_by_count":14,"area":null},{"id":"2409.17264","title":"No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2402.15264","title":"DEEM: Dynamic Experienced Expert Modeling for Stance Detection","created":"2024-02-23","cited_by_count":12,"area":null},{"id":"2406.02616","title":"Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach","created":"2024-06-03","cited_by_count":12,"area":null},{"id":"2409.14254","title":"Instruction Following without Instruction Tuning","created":"2024-09-21","cited_by_count":12,"area":null},{"id":"2409.20246","title":"Analysing Zero-Shot Readability-Controlled Sentence Simplification","created":"2024-09-30","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":"2404.02403","title":"Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT","created":"2024-04-03","cited_by_count":11,"area":null},{"id":"2406.01224","title":"Demonstration Augmentation for Zero-shot In-context Learning","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2412.08258","title":"Large Language Models for Scholarly Ontology Generation: An Extensive Analysis in the Engineering Field","created":"2024-12-11","cited_by_count":10,"area":null},{"id":"2508.04002","title":"CAD-Judge: Toward Efficient Morphological Grading and Verification for Text-to-CAD Generation","created":"2025-08-06","cited_by_count":10,"area":null},{"id":"2510.13855","title":"Harnessing Consistency for Robust Test-Time LLM Ensemble","created":"2025-10-12","cited_by_count":10,"area":null},{"id":"2503.02457","title":"Don't Get Too Excited -- Eliciting Emotions in LLMs","created":"2025-03-04","cited_by_count":9,"area":null},{"id":"2505.13636","title":"Incentivizing Truthful Language Models via Peer Elicitation Games","created":"2025-05-19","cited_by_count":9,"area":null},{"id":"2605.20613","title":"HRM-Text: Efficient Pretraining Beyond Scaling","created":"2026-05-20","cited_by_count":9,"area":null},{"id":"2401.10768","title":"Knowledge Verification to Nip Hallucination in the Bud","created":"2024-01-19","cited_by_count":8,"area":null},{"id":"2404.17336","title":"Introducing cosmosGPT: Monolingual Training for Turkish Language Models","created":"2024-04-26","cited_by_count":8,"area":null},{"id":"2404.18255","title":"PatentGPT: A Large Language Model for Intellectual Property","created":"2024-04-28","cited_by_count":8,"area":null},{"id":"2405.13034","title":"Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality","created":"2024-05-16","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":"2505.18502","title":"Knowledge Fusion of Large Language Models Via Modular SkillPacks","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2506.13044","title":"Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models","created":"2025-06-16","cited_by_count":8,"area":null},{"id":"2507.11261","title":"ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition","created":"2025-07-15","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":"2310.16582","title":"UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2501.04473","title":"When LLMs Struggle: Reference-less Translation Evaluation for Low-resource Languages","created":"2025-01-08","cited_by_count":7,"area":null},{"id":"2503.22562","title":"Niyama : Breaking the Silos of LLM Inference Serving","created":"2025-03-28","cited_by_count":7,"area":null},{"id":"2506.00439","title":"RLAE: Reinforcement Learning-Assisted Ensemble for LLMs","created":"2025-05-31","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":"2512.01556","title":"LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2402.16107","title":"Knowledge Fusion of Chat LLMs: A Preliminary Technical Report","created":"2024-02-25","cited_by_count":6,"area":null},{"id":"2404.04108","title":"Large language models as oracles for instantiating ontologies with domain-specific knowledge","created":"2024-04-05","cited_by_count":6,"area":null},{"id":"2405.19265","title":"AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2406.09952","title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2410.03278","title":"What do Large Language Models Need for Machine Translation Evaluation?","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2311.16673","title":"Large Language Models Meet Computer Vision: A Brief Survey","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2402.10618","title":"Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2504.01472","title":"ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2505.21537","title":"OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2506.21532","title":"\"What's Up, Doc?\": Analyzing How Users Seek Health Information in Large-Scale Conversational AI Datasets","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2509.06274","title":"IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2401.11725","title":"Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models","created":"2024-01-22","cited_by_count":4,"area":null},{"id":"2402.09132","title":"Exploring the Adversarial Capabilities of Large Language Models","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2402.12617","title":"Generative AI Security: Challenges and Countermeasures","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2402.14453","title":"Do LLMs Implicitly Determine the Suitable Text Difficulty for Users?","created":"2024-02-22","cited_by_count":4,"area":null},{"id":"2406.11721","title":"The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2406.12527","title":"FuseGen: PLM Fusion for Data-generation based Zero-shot Learning","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2406.18045","title":"PharmaGPT: Domain-Specific Large Language Models for Bio-Pharmaceutical and Chemistry","created":"2024-06-26","cited_by_count":4,"area":null},{"id":"2407.01384","title":"Free-text Rationale Generation under Readability Level Control","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2505.21657","title":"Explaining Large Language Models with gSMILE","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2604.07892","title":"Data Selection for Multi-turn Dialogue Instruction Tuning","created":"2026-04-09","cited_by_count":4,"area":null},{"id":"2312.14480","title":"MetaAID 2.5: A Secure Framework for Developing Metaverse Applications via Large Language Models","created":"2023-12-22","cited_by_count":3,"area":null},{"id":"2405.12612","title":"Tagengo: A Multilingual Chat Dataset","created":"2024-05-21","cited_by_count":3,"area":null},{"id":"2408.04998","title":"ProFuser: Progressive Fusion of Large Language Models","created":"2024-08-09","cited_by_count":3,"area":null}],"next_cursor":"100"}