{"list":"other","total":56,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437},{"id":"2407.12784","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","created":"2024-07-17","cited_by_count":429},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2410.18451","title":"Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs","created":"2024-10-24","cited_by_count":327},{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237},{"id":"1602.02355","title":"Hyperparameter optimization with approximate gradient","created":"2016-02-07","cited_by_count":233},{"id":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"2311.07689","title":"MART: Improving LLM Safety with Multi-round Automatic Red-Teaming","created":"2023-11-13","cited_by_count":163},{"id":"1611.07476","title":"Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond","created":"2016-11-22","cited_by_count":159},{"id":"2402.10058","title":"Towards Safer Large Language Models through Machine Unlearning","created":"2024-02-15","cited_by_count":139},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135},{"id":"2203.12817","title":"Continual Learning and Private Unlearning","created":"2022-03-24","cited_by_count":130},{"id":"2305.06535","title":"KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment","created":"2023-05-11","cited_by_count":99},{"id":"2406.08607","title":"Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference","created":"2024-06-12","cited_by_count":88},{"id":"2410.11143","title":"LLM Unlearning via Loss Adjustment with Only Forget Data","created":"2024-10-14","cited_by_count":75},{"id":"2404.12038","title":"Uncovering Safety Risks of Large Language Models through Concept Activation Vector","created":"2024-04-18","cited_by_count":67},{"id":"2110.00455","title":"Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond","created":"2021-10-01","cited_by_count":63},{"id":"2310.12962","title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models","created":"2023-10-19","cited_by_count":61},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45},{"id":"2109.11926","title":"Sinkhorn Distributionally Robust Optimization","created":"2021-09-24","cited_by_count":38},{"id":"2309.13793","title":"ReMasker: Imputing Tabular Data with Masked Autoencoding","created":"2023-09-25","cited_by_count":37},{"id":"2110.07004","title":"On the Convergence Theory for Hessian-Free Bilevel Algorithms","created":"2021-10-13","cited_by_count":35},{"id":"2301.03046","title":"STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition","created":"2023-01-08","cited_by_count":29},{"id":"2407.01920","title":"To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models","created":"2024-07-02","cited_by_count":26},{"id":"2411.12103","title":"Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods","created":"2024-11-18","cited_by_count":26},{"id":"2111.04986","title":"Unified Group Fairness on Federated Learning","created":"2021-11-09","cited_by_count":15},{"id":"2401.10809","title":"Neglected Hessian component explains mysteries in Sharpness regularization","created":"2024-01-19","cited_by_count":12},{"id":"2402.17722","title":"Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence","created":"2024-02-27","cited_by_count":11},{"id":"2406.12771","title":"First-Order Methods for Linearly Constrained Bilevel Optimization","created":"2024-06-18","cited_by_count":10},{"id":"2409.05352","title":"PriorDrive: Enhancing Online HD Mapping with Unified Vector Priors","created":"2024-09-09","cited_by_count":10},{"id":"2301.04850","title":"Understanding Difficulty-based Sample Weighting with a Universal Difficulty Measure","created":"2023-01-12","cited_by_count":9},{"id":"2109.12534","title":"Data Summarization via Bilevel Optimization","created":"2021-09-26","cited_by_count":8},{"id":"2311.00858","title":"SmoothHess: ReLU Network Feature Interactions via Stein's Lemma","created":"2023-11-01","cited_by_count":5},{"id":"1705.11041","title":"Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees","created":"2017-05-31","cited_by_count":4},{"id":"2410.09508","title":"CollabEdit: Towards Non-destructive Collaborative Knowledge Editing","created":"2024-10-12","cited_by_count":1}],"next_cursor":null}