{"list":"other","total":69,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"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":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2006.01862","title":"Consistent Estimators for Learning to Defer to an Expert","created":"2020-06-02","cited_by_count":271},{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266},{"id":"1711.06664","title":"Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer","created":"2017-11-17","cited_by_count":233},{"id":"2502.14802","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","created":"2025-02-20","cited_by_count":231},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205},{"id":"2402.19255","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","created":"2024-02-29","cited_by_count":158},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105},{"id":"2203.04291","title":"Learning from Few Examples: A Summary of Approaches to Few-Shot Learning","created":"2022-03-07","cited_by_count":86},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86},{"id":"2202.03673","title":"Calibrated Learning to Defer with One-vs-All Classifiers","created":"2022-02-08","cited_by_count":69},{"id":"2503.13964","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","created":"2025-03-18","cited_by_count":67},{"id":"2403.03870","title":"Learning to Decode Collaboratively with Multiple Language Models","created":"2024-03-06","cited_by_count":62},{"id":"2210.16955","title":"Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles","created":"2022-10-30","cited_by_count":60},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54},{"id":"2507.09477","title":"Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs","created":"2025-07-13","cited_by_count":42},{"id":"2308.07758","title":"Forward-Backward Reasoning in Large Language Models for Mathematical Verification","created":"2023-08-15","cited_by_count":40},{"id":"2405.13021","title":"IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues","created":"2024-05-15","cited_by_count":40},{"id":"2111.04964","title":"On Representation Knowledge Distillation for Graph Neural Networks","created":"2021-11-09","cited_by_count":38},{"id":"2310.14774","title":"Principled Approaches for Learning to Defer with Multiple Experts","created":"2023-10-23","cited_by_count":38},{"id":"2405.16420","title":"M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions","created":"2024-05-26","cited_by_count":38},{"id":"2405.19261","title":"Faster Cascades via Speculative Decoding","created":"2024-05-29","cited_by_count":38},{"id":"2505.03970","title":"A Reasoning-Focused Legal Retrieval Benchmark","created":"2025-05-06","cited_by_count":37},{"id":"2403.19964","title":"FairRAG: Fair Human Generation via Fair Retrieval Augmentation","created":"2024-03-29","cited_by_count":34},{"id":"2310.14770","title":"Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention","created":"2023-10-23","cited_by_count":32},{"id":"2504.12330","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","created":"2025-04-13","cited_by_count":31},{"id":"2403.02683","title":"Learning to Defer to a Population: A Meta-Learning Approach","created":"2024-03-05","cited_by_count":27},{"id":"2403.07213","title":"Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits","created":"2024-03-11","cited_by_count":27},{"id":"2305.16876","title":"CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models","created":"2023-05-23","cited_by_count":26},{"id":"2403.05894","title":"Frequency Attention for Knowledge Distillation","created":"2024-03-09","cited_by_count":24},{"id":"2402.04513","title":"Online Cascade Learning for Efficient Inference over Streams","created":"2024-02-07","cited_by_count":20},{"id":"2208.05642","title":"Self-Knowledge Distillation via Dropout","created":"2022-08-11","cited_by_count":18},{"id":"2406.07212","title":"Trustworthy and Practical AI for Healthcare: A Guided Deferral System with Large Language Models","created":"2024-06-11","cited_by_count":16},{"id":"2405.06683","title":"ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization","created":"2024-05-06","cited_by_count":15},{"id":"2503.10265","title":"SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video Analysis","created":"2025-03-13","cited_by_count":15},{"id":"2502.09054","title":"Cost-Saving LLM Cascades with Early Abstention","created":"2025-02-13","cited_by_count":14},{"id":"2501.09345","title":"Rational Tuning of LLM Cascades via Probabilistic Modeling","created":"2025-01-16","cited_by_count":10},{"id":"2502.13847","title":"DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue","created":"2025-02-19","cited_by_count":10},{"id":"2506.03541","title":"Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement","created":"2025-06-04","cited_by_count":10},{"id":"2407.00072","title":"Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback","created":"2024-06-21","cited_by_count":8},{"id":"2506.10635","title":"Conversational Search: From Fundamentals to Frontiers in the LLM Era","created":"2025-06-12","cited_by_count":8},{"id":"2410.09343","title":"ELICIT: LLM Augmentation via External In-Context Capability","created":"2024-10-12","cited_by_count":7},{"id":"2411.02353","title":"Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generation","created":"2024-11-04","cited_by_count":7},{"id":"2401.13849","title":"TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance","created":"2024-01-24","cited_by_count":6},{"id":"2502.01459","title":"Learning to Partially Defer for Sequences","created":"2025-02-03","cited_by_count":4},{"id":"2506.21098","title":"ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry","created":"2025-06-26","cited_by_count":3},{"id":"2409.16253","title":"Learning To Help: Training Models to Assist Legacy Devices","created":"2024-09-24","cited_by_count":2},{"id":"2501.13810","title":"Learning to Help in Multi-Class Settings","created":"2025-01-23","cited_by_count":2}],"next_cursor":null}