{"list":"other","total":100,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2306.03314","title":"Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents","created":"2023-06-05","cited_by_count":333},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"2309.13007","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","created":"2023-09-22","cited_by_count":309},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260},{"id":"2305.10037","title":"Can Language Models Solve Graph Problems in Natural Language?","created":"2023-05-17","cited_by_count":252},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"2311.10702","title":"Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2","created":"2023-11-17","cited_by_count":229},{"id":"2403.13187","title":"Evolutionary Optimization of Model Merging Recipes","created":"2024-03-19","cited_by_count":208},{"id":"2403.13257","title":"Arcee's MergeKit: A Toolkit for Merging Large Language Models","created":"2024-03-20","cited_by_count":194},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191},{"id":"2402.00367","title":"Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration","created":"2024-02-01","cited_by_count":180},{"id":"2402.18272","title":"Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?","created":"2024-02-28","cited_by_count":159},{"id":"2309.10062","title":"SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models","created":"2023-09-18","cited_by_count":153},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2312.06795","title":"Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks","created":"2023-12-11","cited_by_count":133},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131},{"id":"2402.03578","title":"LLM Multi-Agent Systems: Challenges and Open Problems","created":"2024-02-05","cited_by_count":120},{"id":"2401.10491","title":"Knowledge Fusion of Large Language Models","created":"2024-01-19","cited_by_count":115},{"id":"2311.17371","title":"Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs","created":"2023-11-29","cited_by_count":114},{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113},{"id":"2310.01334","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","created":"2023-10-02","cited_by_count":108},{"id":"2204.08396","title":"StableMoE: Stable Routing Strategy for Mixture of Experts","created":"2022-04-18","cited_by_count":100},{"id":"2110.03742","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","created":"2021-09-24","cited_by_count":96},{"id":"2401.07324","title":"Small LLMs Are Weak Tool Learners: A Multi-LLM Agent","created":"2024-01-14","cited_by_count":93},{"id":"2403.19522","title":"Model Stock: All we need is just a few fine-tuned models","created":"2024-03-28","cited_by_count":92},{"id":"2401.10034","title":"Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap","created":"2024-01-18","cited_by_count":90},{"id":"2401.08565","title":"Tuning Language Models by Proxy","created":"2024-01-16","cited_by_count":89},{"id":"2312.06648","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","created":"2023-12-11","cited_by_count":88},{"id":"2402.00433","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","created":"2024-02-01","cited_by_count":85},{"id":"2404.02183","title":"Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization","created":"2024-04-02","cited_by_count":84},{"id":"2406.11617","title":"DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling","created":"2024-06-17","cited_by_count":81},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80},{"id":"2407.08223","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","created":"2024-07-11","cited_by_count":77},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67},{"id":"2002.05688","title":"Classifying the classifier: dissecting the weight space of neural networks","created":"2020-02-13","cited_by_count":65},{"id":"2305.14705","title":"Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models","created":"2023-05-24","cited_by_count":65},{"id":"2310.17512","title":"CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agents","created":"2023-10-26","cited_by_count":65},{"id":"2403.03870","title":"Learning to Decode Collaboratively with Multiple Language Models","created":"2024-03-06","cited_by_count":62},{"id":"2210.05144","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","created":"2022-10-11","cited_by_count":60},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60},{"id":"2402.18381","title":"Large Language Models As Evolution Strategies","created":"2024-02-28","cited_by_count":58},{"id":"2404.11531","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","created":"2024-04-17","cited_by_count":56},{"id":"2406.15992","title":"Can LLM Graph Reasoning Generalize beyond Pattern Memorization?","created":"2024-06-23","cited_by_count":47},{"id":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46},{"id":"2405.14314","title":"Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration","created":"2024-05-23","cited_by_count":45},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45},{"id":"2402.01620","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","created":"2024-02-02","cited_by_count":43},{"id":"2409.12147","title":"MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning","created":"2024-09-18","cited_by_count":41},{"id":"2401.02412","title":"LLM Augmented LLMs: Expanding Capabilities through Composition","created":"2024-01-04","cited_by_count":35},{"id":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18},{"id":"2311.07682","title":"Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion","created":"2023-11-13","cited_by_count":13},{"id":"2310.01290","title":"Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models","created":"2023-10-02","cited_by_count":11},{"id":"2310.04329","title":"Pika: Empowering Non-Programmers to Author Executable Governance Policies in Online Communities","created":"2023-10-06","cited_by_count":5},{"id":"2311.02394","title":"NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications","created":"2023-11-04","cited_by_count":4}],"next_cursor":null}