{"total":247,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028,"area":null},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104,"area":"alignment"},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839,"area":"rag"},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651,"area":"safety"},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420,"area":"safety"},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988,"area":"lr"},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748,"area":"alignment"},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651,"area":"alignment"},{"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,"area":null},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451,"area":"safety"},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431,"area":"alignment"},{"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,"area":"alignment"},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401,"area":"alignment"},{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398,"area":"mllm"},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266,"area":"safety"},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"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,"area":"safety"},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"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,"area":"alignment"},{"id":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238,"area":"lr"},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2402.06457","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","created":"2024-02-09","cited_by_count":217,"area":"lr"},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192,"area":"alignment"},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175,"area":"safety"},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"id":"2402.09739","title":"QuRating: Selecting High-Quality Data for Training Language Models","created":"2024-02-15","cited_by_count":157,"area":null},{"id":"2402.08567","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","created":"2024-02-13","cited_by_count":153,"area":"mllm"},{"id":"2402.02309","title":"Jailbreaking Attack against Multimodal Large Language Model","created":"2024-02-04","cited_by_count":135,"area":"safety"},{"id":"2306.09442","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","created":"2023-06-15","cited_by_count":114,"area":"safety"},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","cited_by_count":91,"area":null},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2303.14742","title":"Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases","created":"2023-03-26","cited_by_count":86,"area":null},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84,"area":null},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80,"area":"safety"},{"id":"2403.07865","title":"CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion","created":"2024-03-12","cited_by_count":76,"area":"safety"},{"id":"2305.13735","title":"Aligning Large Language Models through Synthetic Feedback","created":"2023-05-23","cited_by_count":75,"area":"alignment"},{"id":"2401.06561","title":"Intention Analysis Makes LLMs A Good Jailbreak Defender","created":"2024-01-12","cited_by_count":74,"area":"alignment"},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2406.01288","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","created":"2024-06-03","cited_by_count":70,"area":"safety"},{"id":"2403.20046","title":"Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning","created":"2024-03-29","cited_by_count":69,"area":"lr"},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"area":null},{"id":"2311.09127","title":"Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts","created":"2023-11-15","cited_by_count":65,"area":"safety"},{"id":"2406.10794","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","created":"2024-06-16","cited_by_count":64,"area":"safety"},{"id":"2311.09410","title":"When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour","created":"2023-11-15","cited_by_count":62,"area":null},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2402.08265","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","created":"2024-02-13","cited_by_count":55,"area":"diffusion"},{"id":"2405.18881","title":"Inference-Time Alignment of Diffusion Models with Direct Noise Optimization","created":"2024-05-29","cited_by_count":55,"area":"diffusion"},{"id":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53,"area":null},{"id":"2309.05274","title":"FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models","created":"2023-09-11","cited_by_count":51,"area":"safety"},{"id":"2402.09674","title":"PAL: Proxy-Guided Black-Box Attack on Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"id":"2408.11491","title":"SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering","created":"2024-08-21","cited_by_count":50,"area":"alignment"},{"id":"2401.06824","title":"Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective","created":"2024-01-12","cited_by_count":48,"area":"safety"},{"id":"2309.11696","title":"LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination","created":"2023-09-21","cited_by_count":46,"area":null},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46,"area":"safety"},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2510.04340","title":"Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time","created":"2025-10-05","cited_by_count":43,"area":null},{"id":"2510.05024","title":"Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment","created":"2025-10-06","cited_by_count":43,"area":"alignment"},{"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,"area":"safety"},{"id":"2312.00027","title":"Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections","created":"2023-11-15","cited_by_count":39,"area":"safety"},{"id":"2501.17315","title":"A sketch of an AI control safety case","created":"2025-01-28","cited_by_count":39,"area":"agents"},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2404.03565","title":"Personalized LLM Response Generation with Parameterized Memory Injection","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2407.12824","title":"Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models","created":"2024-07-02","cited_by_count":32,"area":null},{"id":"2409.11239","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do","created":"2024-09-17","cited_by_count":32,"area":"alignment"},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2409.14703","title":"MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification","created":"2024-09-23","cited_by_count":30,"area":null},{"id":"2309.16155","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF","created":"2023-09-28","cited_by_count":29,"area":"alignment"},{"id":"2404.13968","title":"Protecting Your LLMs with Information Bottleneck","created":"2024-04-22","cited_by_count":29,"area":"safety"},{"id":"2405.02501","title":"PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning","created":"2024-05-03","cited_by_count":29,"area":null},{"id":"2405.16229","title":"No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks","created":"2024-05-25","cited_by_count":29,"area":"alignment"},{"id":"2405.10529","title":"Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors","created":"2024-05-17","cited_by_count":27,"area":"mllm"},{"id":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2303.07610","title":"Exploring ChatGPT's Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences","created":"2023-03-14","cited_by_count":25,"area":null},{"id":"2305.10314","title":"LeTI: Learning to Generate from Textual Interactions","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2406.02575","title":"Cross-Modal Safety Alignment: Is textual unlearning all you need?","created":"2024-05-27","cited_by_count":25,"area":"mllm"},{"id":"2312.12736","title":"Learning and Forgetting Unsafe Examples in Large Language Models","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2408.01420","title":"Mission Impossible: A Statistical Perspective on Jailbreaking LLMs","created":"2024-08-02","cited_by_count":24,"area":"alignment"},{"id":"2305.18449","title":"Taming AI Bots: Controllability of Neural States in Large Language Models","created":"2023-05-29","cited_by_count":22,"area":null},{"id":"2311.08576","title":"Towards Evaluating AI Systems for Moral Status Using Self-Reports","created":"2023-11-14","cited_by_count":22,"area":null},{"id":"2501.01956","title":"Metadata Conditioning Accelerates Language Model Pre-training","created":"2025-01-03","cited_by_count":22,"area":null},{"id":"2508.10975","title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining","created":"2025-08-14","cited_by_count":21,"area":"synth"},{"id":"2304.07854","title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation","created":"2023-04-16","cited_by_count":20,"area":null},{"id":"2404.07242","title":"Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs","created":"2024-04-09","cited_by_count":20,"area":null},{"id":"2407.17915","title":"The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models","created":"2024-07-25","cited_by_count":20,"area":"agents"},{"id":"2605.02087","title":"Model Spec Midtraining: Improving How Alignment Training Generalizes","created":"2026-05-03","cited_by_count":20,"area":null},{"id":"2304.08109","title":"A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model","created":"2023-04-17","cited_by_count":19,"area":null},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null}],"next_cursor":"100"}