{"list":"other","total":56,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"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":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"2501.07301","title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning","created":"2025-01-13","cited_by_count":415},{"id":"1910.12656","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration","created":"2019-10-28","cited_by_count":364},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2502.18581","title":"Scalable Best-of-N Selection for Large Language Models via Self-Certainty","created":"2025-02-25","cited_by_count":187},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115},{"id":"2502.06233","title":"Confidence Improves Self-Consistency in LLMs","created":"2025-02-10","cited_by_count":113},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112},{"id":"2406.08391","title":"Large Language Models Must Be Taught to Know What They Don't Know","created":"2024-06-12","cited_by_count":100},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95},{"id":"2302.13439","title":"Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models","created":"2023-02-26","cited_by_count":91},{"id":"2412.14737","title":"On Verbalized Confidence Scores for LLMs","created":"2024-12-19","cited_by_count":83},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67},{"id":"2305.14613","title":"Selectively Answering Ambiguous Questions","created":"2023-05-24","cited_by_count":66},{"id":"2403.18349","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","created":"2024-03-27","cited_by_count":66},{"id":"2503.01422","title":"Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding","created":"2025-03-03","cited_by_count":63},{"id":"2411.04282","title":"Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding","created":"2024-11-06","cited_by_count":55},{"id":"2503.02623","title":"Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models","created":"2025-03-04","cited_by_count":52},{"id":"2406.11675","title":"BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models","created":"2024-06-17","cited_by_count":50},{"id":"2502.01839","title":"Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification","created":"2025-02-03","cited_by_count":50},{"id":"1506.04416","title":"Bayesian Dark Knowledge","created":"2015-06-14","cited_by_count":45},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37},{"id":"1611.00448","title":"Natural-Parameter Networks: A Class of Probabilistic Neural Networks","created":"2016-11-02","cited_by_count":34},{"id":"2410.14582","title":"Do LLMs estimate uncertainty well in instruction-following?","created":"2024-10-18","cited_by_count":26},{"id":"2307.09254","title":"Selective Generation for Controllable Language Models","created":"2023-07-18","cited_by_count":15},{"id":"2107.14762","title":"On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals","created":"2021-07-30","cited_by_count":14},{"id":"2412.05723","title":"Training-Free Bayesianization for Low-Rank Adapters of Large Language Models","created":"2024-12-07","cited_by_count":12},{"id":"2502.12122","title":"Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA","created":"2025-02-17","cited_by_count":5}],"next_cursor":null}