{"list":"other","total":70,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"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":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"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":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431},{"id":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"2209.15430","title":"Relative representations enable zero-shot latent space communication","created":"2022-09-30","cited_by_count":191},{"id":"2402.05120","title":"More Agents Is All You Need","created":"2024-02-03","cited_by_count":180},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172},{"id":"2311.08692","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","created":"2023-11-15","cited_by_count":145},{"id":"2310.03094","title":"Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning","created":"2023-10-04","cited_by_count":143},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121},{"id":"2109.11377","title":"WRENCH: A Comprehensive Benchmark for Weak Supervision","created":"2021-09-23","cited_by_count":96},{"id":"2308.06077","title":"Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling","created":"2023-08-11","cited_by_count":95},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91},{"id":"2410.10347","title":"A Unified Approach to Routing and Cascading for LLMs","created":"2024-10-14","cited_by_count":80},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67},{"id":"2404.12715","title":"Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration","created":"2024-04-19","cited_by_count":67},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67},{"id":"2202.05433","title":"A Survey on Programmatic Weak Supervision","created":"2022-02-11","cited_by_count":66},{"id":"2403.03870","title":"Learning to Decode Collaboratively with Multiple Language Models","created":"2024-03-06","cited_by_count":62},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60},{"id":"2408.12320","title":"TensorOpera Router: A Multi-Model Router for Efficient LLM Inference","created":"2024-08-22","cited_by_count":60},{"id":"2502.18482","title":"MixLLM: Dynamic Routing in Mixed Large Language Models","created":"2025-02-09","cited_by_count":59},{"id":"2404.11531","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","created":"2024-04-17","cited_by_count":56},{"id":"2310.03046","title":"EcoAssistant: Using LLM Assistant More Affordably and Accurately","created":"2023-10-03","cited_by_count":49},{"id":"2405.00467","title":"Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing","created":"2024-05-01","cited_by_count":46},{"id":"2404.09492","title":"Bridging the Gap between Different Vocabularies for LLM Ensemble","created":"2024-04-15","cited_by_count":45},{"id":"2210.05528","title":"Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems","created":"2022-10-11","cited_by_count":44},{"id":"2305.14628","title":"Getting MoRE out of Mixture of Language Model Reasoning Experts","created":"2023-05-24","cited_by_count":44},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44},{"id":"2410.03953","title":"LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity","created":"2024-10-04","cited_by_count":42},{"id":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41},{"id":"2412.15797","title":"Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning","created":"2024-12-20","cited_by_count":40},{"id":"2409.15518","title":"Eagle: Efficient Training-Free Router for Multi-LLM Inference","created":"2024-09-23","cited_by_count":35},{"id":"2401.13979","title":"Routoo: Learning to Route to Large Language Models Effectively","created":"2024-01-25","cited_by_count":34},{"id":"2502.02743","title":"LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing","created":"2025-02-04","cited_by_count":34},{"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},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31},{"id":"2502.01976","title":"CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing","created":"2025-02-04","cited_by_count":30},{"id":"2502.14855","title":"Prompt-to-Leaderboard","created":"2025-02-20","cited_by_count":30},{"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},{"id":"2401.02994","title":"Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM","created":"2024-01-04","cited_by_count":27},{"id":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25},{"id":"2410.21520","title":"LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation","created":"2024-10-28","cited_by_count":25},{"id":"2502.11021","title":"Leveraging Uncertainty Estimation for Efficient LLM Routing","created":"2025-02-16","cited_by_count":21},{"id":"2411.04424","title":"Bayesian Calibration of Win Rate Estimation with LLM Evaluators","created":"2024-11-07","cited_by_count":16},{"id":"2412.12170","title":"PickLLM: Context-Aware RL-Assisted Large Language Model Routing","created":"2024-12-12","cited_by_count":13},{"id":"2407.19807","title":"Cool-Fusion: Fuse Large Language Models without Training","created":"2024-07-29","cited_by_count":12},{"id":"2502.01662","title":"Fast Large Language Model Collaborative Decoding via Speculation","created":"2025-02-01","cited_by_count":12},{"id":"2206.09315","title":"Knowledge Learning with Crowdsourcing: A Brief Review and Systematic Perspective","created":"2022-06-19","cited_by_count":11},{"id":"2402.17982","title":"Collaborative decoding of critical tokens for boosting factuality of large language models","created":"2024-02-28","cited_by_count":9},{"id":"2408.08545","title":"SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models","created":"2024-08-16","cited_by_count":8},{"id":"2409.18583","title":"Hit the Sweet Spot! Span-Level Ensemble for Large Language Models","created":"2024-09-27","cited_by_count":8},{"id":"2403.08281","title":"Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models","created":"2024-03-13","cited_by_count":7},{"id":"2412.04167","title":"Bench-CoE: a Framework for Collaboration of Experts from Benchmark","created":"2024-12-05","cited_by_count":7},{"id":"2310.13961","title":"Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs","created":"2023-10-21","cited_by_count":6},{"id":"2405.08373","title":"PromptMind Team at MEDIQA-CORR 2024: Improving Clinical Text Correction with Error Categorization and LLM Ensembles","created":"2024-05-14","cited_by_count":6},{"id":"2310.13561","title":"Cache & Distil: Optimising API Calls to Large Language Models","created":"2023-10-20","cited_by_count":4},{"id":"2309.05086","title":"Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler","created":"2023-09-10","cited_by_count":3}],"next_cursor":null}