{"list":"other","total":74,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"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":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"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":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"2309.07875","title":"Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions","created":"2023-09-14","cited_by_count":387},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243},{"id":"1802.02246","title":"Approximation Methods for Bilevel Programming","created":"2018-02-06","cited_by_count":236},{"id":"1703.01785","title":"Forward and Reverse Gradient-Based Hyperparameter Optimization","created":"2017-03-06","cited_by_count":234},{"id":"1602.02355","title":"Hyperparameter optimization with approximate gradient","created":"2016-02-07","cited_by_count":233},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185},{"id":"2402.05749","title":"Generalized Preference Optimization: A Unified Approach to Offline Alignment","created":"2024-02-08","cited_by_count":157},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155},{"id":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120},{"id":"2404.01099","title":"What is in Your Safe Data? Identifying Benign Data that Breaks Safety","created":"2024-04-01","cited_by_count":118},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115},{"id":"2308.07074","title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models","created":"2023-08-14","cited_by_count":109},{"id":"2102.07367","title":"A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum","created":"2021-02-15","cited_by_count":106},{"id":"2209.08709","title":"BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach","created":"2022-09-19","cited_by_count":105},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105},{"id":"2308.13320","title":"Fine-tuning can cripple your foundation model; preserving features may be the solution","created":"2023-08-25","cited_by_count":96},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96},{"id":"2405.18641","title":"Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-05-28","cited_by_count":92},{"id":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87},{"id":"2402.04833","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","created":"2024-02-07","cited_by_count":85},{"id":"2006.04045","title":"A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton","created":"2020-06-07","cited_by_count":79},{"id":"1702.03999","title":"A First Order Method for Solving Convex Bi-Level Optimization Problems","created":"2017-02-13","cited_by_count":67},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","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":"2309.01753","title":"On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation","created":"2023-09-04","cited_by_count":51},{"id":"2405.17374","title":"Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models","created":"2024-05-27","cited_by_count":46},{"id":"2402.06886","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","created":"2024-02-10","cited_by_count":41},{"id":"2405.09055","title":"A safety realignment framework via subspace-oriented model fusion for large language models","created":"2024-05-15","cited_by_count":41},{"id":"2403.01081","title":"LAB: Large-Scale Alignment for ChatBots","created":"2024-03-02","cited_by_count":39},{"id":"2406.09289","title":"Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models","created":"2024-06-13","cited_by_count":37},{"id":"2406.19976","title":"ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting","created":"2024-06-28","cited_by_count":37},{"id":"2205.14224","title":"Will Bilevel Optimizers Benefit from Loops","created":"2022-05-27","cited_by_count":36},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34},{"id":"2405.02774","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","created":"2024-05-05","cited_by_count":32},{"id":"2306.12067","title":"Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions","created":"2023-06-21","cited_by_count":31},{"id":"2102.07976","title":"A General Descent Aggregation Framework for Gradient-based Bi-level Optimization","created":"2021-02-16","cited_by_count":28},{"id":"2206.00457","title":"Automatic differentiation of nonsmooth iterative algorithms","created":"2022-05-31","cited_by_count":25},{"id":"2312.12736","title":"Learning and Forgetting Unsafe Examples in Large Language Models","created":"2023-12-20","cited_by_count":24},{"id":"2206.10414","title":"A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences","created":"2022-06-21","cited_by_count":17},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15}],"next_cursor":null}