{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"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":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2212.00490","title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model","created":"2022-12-01","cited_by_count":583},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308},{"id":"2311.08268","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","created":"2023-11-14","cited_by_count":259},{"id":"2410.02355","title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models","created":"2024-10-03","cited_by_count":236},{"id":"2404.03027","title":"JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks","created":"2024-04-03","cited_by_count":230},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206},{"id":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156},{"id":"2103.07113","title":"Training Networks in Null Space of Feature Covariance for Continual Learning","created":"2021-03-12","cited_by_count":143},{"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":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105},{"id":"2406.05644","title":"How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States","created":"2024-06-09","cited_by_count":98},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80},{"id":"2406.10794","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","created":"2024-06-16","cited_by_count":64},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48},{"id":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43},{"id":"2504.09466","title":"AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender","created":"2025-04-13","cited_by_count":38},{"id":"2503.11314","title":"Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering","created":"2025-03-14","cited_by_count":36},{"id":"2410.04962","title":"Activation Scaling for Steering and Interpreting Language Models","created":"2024-10-07","cited_by_count":35},{"id":"2502.12520","title":"SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning","created":"2025-02-18","cited_by_count":32},{"id":"2410.02298","title":"Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models","created":"2024-10-03","cited_by_count":23},{"id":"2506.03292","title":"HyperSteer: Activation Steering at Scale with Hypernetworks","created":"2025-06-03","cited_by_count":23},{"id":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21},{"id":"2503.14963","title":"Continual Multimodal Contrastive Learning","created":"2025-03-19","cited_by_count":20},{"id":"2407.05441","title":"Language Representations Can be What Recommenders Need: Findings and Potentials","created":"2024-07-07","cited_by_count":18},{"id":"2405.14488","title":"MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability","created":"2024-05-23","cited_by_count":15},{"id":"2505.20309","title":"Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs","created":"2025-05-22","cited_by_count":8}],"next_cursor":null}