{"total":180,"rows":[{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569,"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":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2311.04076","title":"Do LLMs exhibit human-like response biases? A case study in survey design","created":"2023-11-07","cited_by_count":180,"area":null},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159,"area":null},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150,"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":"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":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123,"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":"2312.00738","title":"SeaLLMs -- Large Language Models for Southeast Asia","created":"2023-12-01","cited_by_count":104,"area":null},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96,"area":null},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"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":"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":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2401.01523","title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse","created":"2024-01-03","cited_by_count":52,"area":null},{"id":"2309.09530","title":"Adapting Large Language Models to Domains via Reading Comprehension","created":"2023-09-18","cited_by_count":50,"area":null},{"id":"2310.10632","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","created":"2023-10-16","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":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","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":"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":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"area":null},{"id":"2405.13769","title":"Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation","created":"2024-05-22","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":"2310.11244","title":"Entity Matching using Large Language Models","created":"2023-10-17","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":"2403.09057","title":"A Continued Pretrained LLM Approach for Automatic Medical Note Generation","created":"2024-03-14","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":"2402.02318","title":"Diversity Measurement and Subset Selection for Instruction Tuning Datasets","created":"2024-02-04","cited_by_count":29,"area":null},{"id":"2405.07490","title":"Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning","created":"2024-05-13","cited_by_count":28,"area":null},{"id":"2408.10943","title":"SysBench: Can Large Language Models Follow System Messages?","created":"2024-08-20","cited_by_count":28,"area":null},{"id":"2308.04709","title":"A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrology","created":"2023-08-09","cited_by_count":26,"area":null},{"id":"2508.13152","title":"RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns","created":"2025-08-18","cited_by_count":24,"area":null},{"id":"2310.19792","title":"The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metrics","created":"2023-10-30","cited_by_count":23,"area":null},{"id":"2402.06900","title":"Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric","created":"2024-02-10","cited_by_count":23,"area":null},{"id":"2309.03852","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","created":"2023-09-07","cited_by_count":22,"area":null},{"id":"2401.07955","title":"A Study on Large Language Models' Limitations in Multiple-Choice Question Answering","created":"2024-01-15","cited_by_count":22,"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":"2312.01678","title":"Jellyfish: A Large Language Model for Data Preprocessing","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2308.00189","title":"Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?","created":"2023-07-31","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":"2404.01954","title":"HyperCLOVA X Technical Report","created":"2024-04-02","cited_by_count":18,"area":null},{"id":"2405.07518","title":"SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts","created":"2024-05-13","cited_by_count":18,"area":null},{"id":"2405.13684","title":"CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models","created":"2024-05-22","cited_by_count":18,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2412.09560","title":"Foundational Large Language Models for Materials Research","created":"2024-12-12","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":"2402.11111","title":"Language Models as Science Tutors","created":"2024-02-16","cited_by_count":17,"area":null},{"id":"2406.18528","title":"PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation","created":"2024-06-26","cited_by_count":16,"area":null},{"id":"2307.03539","title":"Large Language Models as Batteries-Included Zero-Shot ESCO Skills Matchers","created":"2023-07-07","cited_by_count":15,"area":null},{"id":"2310.09518","title":"Instruction Tuning with Human Curriculum","created":"2023-10-14","cited_by_count":15,"area":null},{"id":"2404.16621","title":"Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare","created":"2024-04-25","cited_by_count":15,"area":null},{"id":"2503.01155","title":"Nature-Inspired Population-Based Evolution of Large Language Models","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2311.03754","title":"Which is better? Exploring Prompting Strategy For LLM-based Metrics","created":"2023-11-07","cited_by_count":14,"area":null},{"id":"2312.15713","title":"PersianLLaMA: Towards Building First Persian Large Language Model","created":"2023-12-25","cited_by_count":14,"area":null},{"id":"2410.02425","title":"LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services","created":"2024-10-03","cited_by_count":14,"area":null},{"id":"2310.11532","title":"Multi-stage Large Language Model Correction for Speech Recognition","created":"2023-10-17","cited_by_count":13,"area":null},{"id":"2401.01916","title":"AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2402.03099","title":"Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2402.12621","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2311.01235","title":"Advancing the Search Frontier with AI Agents","created":"2023-11-02","cited_by_count":12,"area":null},{"id":"2407.08995","title":"Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs","created":"2024-07-12","cited_by_count":12,"area":null},{"id":"2508.11953","title":"Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models","created":"2025-08-16","cited_by_count":12,"area":null},{"id":"2402.09136","title":"DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2404.00560","title":"A Theory for Length Generalization in Learning to Reason","created":"2024-03-31","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":"2412.15184","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2309.16573","title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2311.07592","title":"Hallucination-minimized Data-to-answer Framework for Financial Decision-makers","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2401.16818","title":"H2O-Danube-1.8B Technical Report","created":"2024-01-30","cited_by_count":9,"area":null},{"id":"2403.12848","title":"Planner3D: LLM-enhanced graph prior meets 3D indoor scene explicit regularization","created":"2024-03-19","cited_by_count":9,"area":null},{"id":"2410.12164","title":"Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning","created":"2024-10-16","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":"2312.14751","title":"Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2401.06466","title":"PersianMind: A Cross-Lingual Persian-English Large Language Model","created":"2024-01-12","cited_by_count":7,"area":null},{"id":"2409.10064","title":"MindGuard: Towards Accessible and Sitgma-free Mental Health First Aid via Edge LLM","created":"2024-09-16","cited_by_count":7,"area":null},{"id":"2511.07074","title":"Importance-Aware Data Selection for Efficient LLM Instruction Tuning","created":"2025-11-10","cited_by_count":7,"area":null},{"id":"2309.11063","title":"XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates","created":"2023-09-20","cited_by_count":6,"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":"2407.16724","title":"Structure-aware Domain Knowledge Injection for Large Language Models","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2408.11650","title":"CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2409.19750","title":"AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy","created":"2024-09-29","cited_by_count":6,"area":null},{"id":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","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":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2310.10808","title":"If the Sources Could Talk: Evaluating Large Language Models for Research Assistance in History","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2408.05457","title":"Investigating Instruction Tuning Large Language Models on Graphs","created":"2024-08-10","cited_by_count":5,"area":null},{"id":"2501.14912","title":"Feasible Learning","created":"2025-01-24","cited_by_count":5,"area":null}],"next_cursor":"100"}