{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"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":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"1910.12656","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration","created":"2019-10-28","cited_by_count":364},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"2501.00656","title":"2 OLMo 2 Furious","created":"2024-12-31","cited_by_count":340},{"id":"1909.10155","title":"Verified Uncertainty Calibration","created":"2019-09-23","cited_by_count":309},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185},{"id":"2012.07923","title":"Improving model calibration with accuracy versus uncertainty optimization","created":"2020-12-14","cited_by_count":123},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112},{"id":"2405.20974","title":"SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales","created":"2024-05-31","cited_by_count":105},{"id":"2210.04714","title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","created":"2022-10-10","cited_by_count":104},{"id":"2108.00106","title":"Soft Calibration Objectives for Neural Networks","created":"2021-07-30","cited_by_count":92},{"id":"2006.10564","title":"Distribution-free binary classification: prediction sets, confidence intervals and calibration","created":"2020-06-18","cited_by_count":79},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70},{"id":"2203.07835","title":"Better Uncertainty Calibration via Proper Scores for Classification and Beyond","created":"2022-03-15","cited_by_count":65},{"id":"2205.10183","title":"Prototypical Calibration for Few-shot Learning of Language Models","created":"2022-05-20","cited_by_count":58},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57},{"id":"2207.06211","title":"Sample-dependent Adaptive Temperature Scaling for Improved Calibration","created":"2022-07-13","cited_by_count":48},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47},{"id":"2210.07810","title":"A Consistent and Differentiable Lp Canonical Calibration Error Estimator","created":"2022-10-13","cited_by_count":47},{"id":"2105.04656","title":"Distribution-free calibration guarantees for histogram binning without sample splitting","created":"2021-05-10","cited_by_count":45},{"id":"2404.17287","title":"When to Trust LLMs: Aligning Confidence with Response Quality","created":"2024-04-26","cited_by_count":43},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41},{"id":"2206.02757","title":"Robust Calibration with Multi-domain Temperature Scaling","created":"2022-06-06","cited_by_count":39},{"id":"2403.08819","title":"Thermometer: Towards Universal Calibration for Large Language Models","created":"2024-02-20","cited_by_count":38},{"id":"2312.10584","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","created":"2023-12-17","cited_by_count":35},{"id":"2503.10990","title":"Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium","created":"2025-03-14","cited_by_count":23},{"id":"2404.10315","title":"Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience","created":"2024-04-16","cited_by_count":21},{"id":"2310.10266","title":"Generative Calibration for In-context Learning","created":"2023-10-16","cited_by_count":20},{"id":"2410.16714","title":"Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment","created":"2024-10-22","cited_by_count":20},{"id":"2401.12406","title":"Enhancing In-context Learning via Linear Probe Calibration","created":"2024-01-22","cited_by_count":16},{"id":"2407.07089","title":"Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic","created":"2024-07-09","cited_by_count":14},{"id":"2305.10886","title":"Minimum-Risk Recalibration of Classifiers","created":"2023-05-18","cited_by_count":10},{"id":"2405.15709","title":"Information-theoretic Generalization Analysis for Expected Calibration Error","created":"2024-05-24","cited_by_count":10},{"id":"2310.06182","title":"PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization","created":"2023-10-09","cited_by_count":9},{"id":"2406.06227","title":"PAC-Bayes Analysis for Recalibration in Classification","created":"2024-06-10","cited_by_count":4},{"id":"2405.01817","title":"Uniformly Stable Algorithms for Adversarial Training and Beyond","created":"2024-05-03","cited_by_count":2}],"next_cursor":null}