{"list":"other","total":51,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"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":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"1910.12430","title":"Differentiable Convex Optimization Layers","created":"2019-10-28","cited_by_count":465},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431},{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336},{"id":"2312.14197","title":"Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models","created":"2023-12-21","cited_by_count":264},{"id":"2402.14762","title":"MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues","created":"2024-02-22","cited_by_count":250},{"id":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"2308.07308","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","created":"2023-08-14","cited_by_count":244},{"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":"2404.12358","title":"From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function","created":"2024-04-18","cited_by_count":242},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234},{"id":"2312.06942","title":"AI Control: Improving Safety Despite Intentional Subversion","created":"2023-12-12","cited_by_count":229},{"id":"2105.15183","title":"Efficient and Modular Implicit Differentiation","created":"2021-05-31","cited_by_count":203},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192},{"id":"2501.18837","title":"Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming","created":"2025-01-31","cited_by_count":181},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124},{"id":"2307.14692","title":"Backdoor Attacks for In-Context Learning with Language Models","created":"2023-07-27","cited_by_count":96},{"id":"2405.06624","title":"Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems","created":"2024-05-10","cited_by_count":96},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80},{"id":"2402.16459","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","created":"2024-02-26","cited_by_count":70},{"id":"2403.02475","title":"Enhancing LLM Safety via Constrained Direct Preference Optimization","created":"2024-03-04","cited_by_count":49},{"id":"2405.07932","title":"PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition","created":"2024-05-13","cited_by_count":35},{"id":"2211.12312","title":"Interpreting Neural Networks through the Polytope Lens","created":"2022-11-22","cited_by_count":33},{"id":"2404.11049","title":"Stepwise Alignment for Constrained Language Model Policy Optimization","created":"2024-04-17","cited_by_count":30},{"id":"2305.16147","title":"Learning Safety Constraints from Demonstrations with Unknown Rewards","created":"2023-05-25","cited_by_count":19},{"id":"2306.05426","title":"SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking","created":"2023-06-08","cited_by_count":13},{"id":"2408.05094","title":"Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts","created":"2024-08-09","cited_by_count":9},{"id":"2412.09734","title":"MPAX: Mathematical Programming in JAX","created":"2024-12-12","cited_by_count":7},{"id":"2410.19933","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","created":"2024-10-25","cited_by_count":5},{"id":"1805.09719","title":"Learning convex polyhedra with margin","created":"2018-05-24","cited_by_count":4}],"next_cursor":null}