{"total":255,"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":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464,"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":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613,"area":null},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487,"area":null},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377,"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":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2310.13023","title":"GraphGPT: Graph Instruction Tuning for Large Language Models","created":"2023-10-19","cited_by_count":226,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149,"area":null},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142,"area":null},{"id":"2309.10621","title":"Large language models can accurately predict searcher preferences","created":"2023-09-19","cited_by_count":131,"area":null},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128,"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":"2401.10491","title":"Knowledge Fusion of Large Language Models","created":"2024-01-19","cited_by_count":115,"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":"2308.07074","title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models","created":"2023-08-14","cited_by_count":109,"area":null},{"id":"2402.10172","title":"OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models","created":"2024-02-15","cited_by_count":109,"area":null},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108,"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":"2310.15123","title":"Branch-Solve-Merge Improves Large Language Model Evaluation and Generation","created":"2023-10-23","cited_by_count":106,"area":null},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2401.02415","title":"LLaMA Pro: Progressive LLaMA with Block Expansion","created":"2024-01-04","cited_by_count":101,"area":null},{"id":"2406.16008","title":"Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization","created":"2024-06-23","cited_by_count":101,"area":null},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97,"area":null},{"id":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","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":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2306.09296","title":"KoLA: Carefully Benchmarking World Knowledge of Large Language Models","created":"2023-06-15","cited_by_count":85,"area":null},{"id":"2310.10638","title":"In-context Pretraining: Language Modeling Beyond Document Boundaries","created":"2023-10-16","cited_by_count":79,"area":null},{"id":"2311.14736","title":"Data Diversity Matters for Robust Instruction Tuning","created":"2023-11-21","cited_by_count":76,"area":null},{"id":"2405.08011","title":"A Survey of Large Language Models for Graphs","created":"2024-05-10","cited_by_count":72,"area":null},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72,"area":null},{"id":"2308.04948","title":"Extrapolating Large Language Models to Non-English by Aligning Languages","created":"2023-08-09","cited_by_count":69,"area":null},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69,"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":"2404.13081","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","created":"2024-04-17","cited_by_count":67,"area":null},{"id":"2307.06018","title":"PolyLM: An Open Source Polyglot Large Language Model","created":"2023-07-12","cited_by_count":64,"area":null},{"id":"2403.03870","title":"Learning to Decode Collaboratively with Multiple Language Models","created":"2024-03-06","cited_by_count":62,"area":null},{"id":"2407.00952","title":"SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2024-07-01","cited_by_count":62,"area":null},{"id":"2311.00288","title":"Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks","created":"2023-11-01","cited_by_count":55,"area":null},{"id":"2402.12847","title":"Instruction-tuned Language Models are Better Knowledge Learners","created":"2024-02-20","cited_by_count":55,"area":null},{"id":"2403.19211","title":"Dual-Personalizing Adapter for Federated Foundation Models","created":"2024-03-28","cited_by_count":55,"area":null},{"id":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54,"area":null},{"id":"2312.15407","title":"A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators","created":"2023-12-24","cited_by_count":45,"area":null},{"id":"2403.18058","title":"COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning","created":"2024-03-26","cited_by_count":45,"area":null},{"id":"2407.06645","title":"Entropy Law: The Story Behind Data Compression and LLM Performance","created":"2024-07-09","cited_by_count":44,"area":null},{"id":"2312.10302","title":"One-Shot Learning as Instruction Data Prospector for Large Language Models","created":"2023-12-16","cited_by_count":43,"area":null},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2311.08711","title":"PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning","created":"2023-11-15","cited_by_count":39,"area":null},{"id":"2311.09278","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","created":"2023-11-15","cited_by_count":39,"area":null},{"id":"2401.07950","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","created":"2024-01-15","cited_by_count":39,"area":null},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39,"area":null},{"id":"2502.01968","title":"Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning","created":"2025-02-04","cited_by_count":39,"area":null},{"id":"2406.19976","title":"ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting","created":"2024-06-28","cited_by_count":37,"area":null},{"id":"2308.11764","title":"Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models","created":"2023-08-22","cited_by_count":36,"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":"2406.10323","title":"GenQA: Generating Millions of Instructions from a Handful of Prompts","created":"2024-06-14","cited_by_count":35,"area":null},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35,"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":"2404.16966","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks","created":"2024-04-25","cited_by_count":31,"area":null},{"id":"2405.12130","title":"MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning","created":"2024-05-20","cited_by_count":31,"area":null},{"id":"2312.02436","title":"MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following","created":"2023-12-05","cited_by_count":30,"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":"2407.15235","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","created":"2024-07-21","cited_by_count":30,"area":null},{"id":"2401.14280","title":"RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization","created":"2024-01-25","cited_by_count":29,"area":null},{"id":"2402.02318","title":"Diversity Measurement and Subset Selection for Instruction Tuning Datasets","created":"2024-02-04","cited_by_count":29,"area":null},{"id":"2403.04945","title":"MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation","created":"2024-03-07","cited_by_count":29,"area":null},{"id":"2410.10877","title":"Improving Data Efficiency via Curating LLM-Driven Rating Systems","created":"2024-10-09","cited_by_count":29,"area":null},{"id":"2310.20111","title":"Making Large Language Models Better Data Creators","created":"2023-10-31","cited_by_count":28,"area":null},{"id":"2403.12776","title":"Automated Data Curation for Robust Language Model Fine-Tuning","created":"2024-03-19","cited_by_count":27,"area":null},{"id":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26,"area":null},{"id":"2401.16405","title":"Scaling Sparse Fine-Tuning to Large Language Models","created":"2024-01-29","cited_by_count":26,"area":null},{"id":"2404.18923","title":"Holmes: A Benchmark to Assess the Linguistic Competence of Language Models","created":"2024-04-29","cited_by_count":26,"area":null},{"id":"2311.01270","title":"People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection","created":"2023-11-02","cited_by_count":25,"area":null},{"id":"2405.02743","title":"Beyond Performance: Quantifying and Mitigating Label Bias in LLMs","created":"2024-05-04","cited_by_count":25,"area":null},{"id":"2311.00233","title":"Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions","created":"2023-11-01","cited_by_count":24,"area":null},{"id":"2401.17585","title":"Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks","created":"2024-01-31","cited_by_count":24,"area":null},{"id":"2401.06692","title":"An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models","created":"2024-01-12","cited_by_count":23,"area":null},{"id":"2404.04042","title":"Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer","created":"2024-04-05","cited_by_count":23,"area":null},{"id":"2410.09300","title":"Nudging: Inference-time Alignment of LLMs via Guided Decoding","created":"2024-10-11","cited_by_count":23,"area":null},{"id":"2501.12147","title":"Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities","created":"2025-01-21","cited_by_count":23,"area":null},{"id":"2402.06126","title":"Learn To be Efficient: Build Structured Sparsity in Large Language Models","created":"2024-02-09","cited_by_count":20,"area":null},{"id":"2403.04780","title":"Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining","created":"2024-03-02","cited_by_count":20,"area":null},{"id":"2407.02030","title":"Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis","created":"2024-07-02","cited_by_count":20,"area":null},{"id":"2409.14396","title":"Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape","created":"2024-09-22","cited_by_count":20,"area":null},{"id":"2510.19178","title":"Imbalanced Gradients in RL Post-Training of Multi-Task LLMs","created":"2025-10-22","cited_by_count":20,"area":null},{"id":"2308.04275","title":"In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning","created":"2023-08-08","cited_by_count":19,"area":null},{"id":"2402.16141","title":"PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization","created":"2024-02-25","cited_by_count":19,"area":null},{"id":"2407.05216","title":"Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course","created":"2024-07-07","cited_by_count":19,"area":null},{"id":"2402.17355","title":"RECOST: External Knowledge Guided Data-efficient Instruction Tuning","created":"2024-02-27","cited_by_count":18,"area":null},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18,"area":null},{"id":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2310.11451","title":"Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective","created":"2023-10-17","cited_by_count":17,"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}],"next_cursor":"100"}