{"list":"other","total":58,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"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":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"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":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415},{"id":"2402.10260","title":"A StrongREJECT for Empty Jailbreaks","created":"2024-02-15","cited_by_count":385},{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360},{"id":"2507.21509","title":"Persona Vectors: Monitoring and Controlling Character Traits in Language Models","created":"2025-07-29","cited_by_count":345},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308},{"id":"2305.02547","title":"PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits","created":"2023-05-04","cited_by_count":234},{"id":"2402.05044","title":"SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models","created":"2024-02-07","cited_by_count":228},{"id":"2311.03348","title":"Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation","created":"2023-11-06","cited_by_count":214},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208},{"id":"2307.00184","title":"Personality Traits in Large Language Models","created":"2023-07-01","cited_by_count":169},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134},{"id":"2206.07550","title":"Evaluating and Inducing Personality in Pre-trained Language Models","created":"2022-05-20","cited_by_count":123},{"id":"2503.00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","created":"2025-03-01","cited_by_count":122},{"id":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115},{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99},{"id":"2504.07128","title":"DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning","created":"2025-04-02","cited_by_count":92},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91},{"id":"2601.10387","title":"The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models","created":"2026-01-15","cited_by_count":90},{"id":"2507.11878","title":"LLMs Encode Harmfulness and Refusal Separately","created":"2025-07-16","cited_by_count":88},{"id":"2406.14144","title":"Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons","created":"2024-06-20","cited_by_count":53},{"id":"2410.16491","title":"BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data","created":"2024-10-21","cited_by_count":50},{"id":"2502.09674","title":"The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions","created":"2025-02-13","cited_by_count":41},{"id":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40},{"id":"2603.05488","title":"Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought","created":"2026-03-05","cited_by_count":40},{"id":"2508.04826","title":"Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History","created":"2025-08-06","cited_by_count":26},{"id":"2310.02168","title":"Editing Personality for Large Language Models","created":"2023-10-03","cited_by_count":22},{"id":"2502.20968","title":"Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs","created":"2025-02-28","cited_by_count":22},{"id":"2502.12566","title":"Exploring the Impact of Personality Traits on LLM Bias and Toxicity","created":"2025-02-18","cited_by_count":14},{"id":"2507.22171","title":"Enhancing Jailbreak Attacks on LLMs via Persona Prompts","created":"2025-07-28","cited_by_count":11},{"id":"2603.24543","title":"Analysing the Safety Pitfalls of Steering Vectors","created":"2026-03-25","cited_by_count":10},{"id":"2505.17650","title":"Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?","created":"2025-05-23","cited_by_count":9},{"id":"2512.17639","title":"Linear Personality Probing and Steering in LLMs: A Big Five Study","created":"2025-12-19","cited_by_count":9},{"id":"2603.18507","title":"Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM","created":"2026-03-19","cited_by_count":9},{"id":"2602.04896","title":"Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models","created":"2026-02-03","cited_by_count":8},{"id":"2502.20757","title":"The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents","created":"2025-02-28","cited_by_count":7},{"id":"2506.13726","title":"Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models","created":"2025-06-16","cited_by_count":7},{"id":"2602.07276","title":"Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs","created":"2026-02-07","cited_by_count":7},{"id":"2604.08524","title":"What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal","created":"2026-04-09","cited_by_count":7},{"id":"2602.15847","title":"Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models","created":"2026-01-23","cited_by_count":5},{"id":"2505.24539","title":"Localizing Persona Representations in LLMs","created":"2025-05-30","cited_by_count":3},{"id":"2512.07092","title":"The Geometry of Persona: Disentangling Personality from Reasoning in Large Language Models","created":"2025-12-08","cited_by_count":3},{"id":"2601.05376","title":"The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models","created":"2026-01-08","cited_by_count":3},{"id":"2512.01247","title":"Benchmarking and Understanding Safety Risks in AI Character Platforms","created":"2025-12-01","cited_by_count":2},{"id":"2512.18244","title":"Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation","created":"2025-12-20","cited_by_count":2},{"id":"2602.13234","title":"Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents","created":"2026-01-29","cited_by_count":2}],"next_cursor":null}