{"total":45,"rows":[{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104,"area":"alignment"},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"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":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651,"area":"alignment"},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2410.05451","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","created":"2024-10-07","cited_by_count":210,"area":"alignment"},{"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,"area":"alignment"},{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144,"area":"alignment"},{"id":"2403.17710","title":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","created":"2024-03-26","cited_by_count":143,"area":"alignment"},{"id":"2311.14455","title":"Universal Jailbreak Backdoors from Poisoned Human Feedback","created":"2023-11-24","cited_by_count":128,"area":"alignment"},{"id":"2402.11746","title":"Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic","created":"2024-02-19","cited_by_count":112,"area":"alignment"},{"id":"2310.15140","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","created":"2023-10-23","cited_by_count":111,"area":"alignment"},{"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,"area":"alignment"},{"id":"2402.09063","title":"Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space","created":"2024-02-14","cited_by_count":91,"area":"alignment"},{"id":"2402.16192","title":"Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing","created":"2024-02-25","cited_by_count":74,"area":"alignment"},{"id":"2402.12329","title":"Query-Based Adversarial Prompt Generation","created":"2024-02-19","cited_by_count":62,"area":"alignment"},{"id":"2404.16369","title":"Don't Say No: Jailbreaking LLM by Suppressing Refusal","created":"2024-04-25","cited_by_count":56,"area":"alignment"},{"id":"2405.17374","title":"Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models","created":"2024-05-27","cited_by_count":46,"area":"alignment"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"id":"2405.20653","title":"Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries","created":"2024-05-31","cited_by_count":28,"area":"alignment"},{"id":"2408.01420","title":"Mission Impossible: A Statistical Perspective on Jailbreaking LLMs","created":"2024-08-02","cited_by_count":24,"area":"alignment"},{"id":"2410.01174","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":"alignment"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2505.17598","title":"One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs","created":"2025-05-23","cited_by_count":12,"area":"alignment"},{"id":"2312.06924","title":"Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack","created":"2023-12-12","cited_by_count":11,"area":"alignment"},{"id":"2502.15435","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","created":"2025-02-21","cited_by_count":10,"area":"alignment"},{"id":"2505.17072","title":"Safety Alignment Can Be Not Superficial With Explicit Safety Signals","created":"2025-05-19","cited_by_count":9,"area":"alignment"},{"id":"2508.05775","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","created":"2025-08-07","cited_by_count":9,"area":"alignment"},{"id":"2510.05052","title":"Proactive defense against LLM Jailbreak","created":"2025-10-06","cited_by_count":7,"area":"alignment"},{"id":"2502.00657","title":"LLM Safety Alignment is Divergence Estimation in Disguise","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2406.07971","title":"It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2412.07192","title":"PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips","created":"2024-12-10","cited_by_count":5,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2506.07402","title":"Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures","created":"2025-06-09","cited_by_count":3,"area":"alignment"},{"id":"2509.19360","title":"Semantic Representation Attack against Aligned Large Language Models","created":"2025-09-18","cited_by_count":3,"area":"alignment"},{"id":"2508.14853","title":"Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent","created":"2025-08-20","cited_by_count":2,"area":"alignment"},{"id":"2506.00676","title":"SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning","created":"2025-05-31","cited_by_count":1,"area":"alignment"},{"id":"2511.00509","title":"Reimagining Safety Alignment with An Image","created":"2025-11-01","cited_by_count":1,"area":"alignment"},{"id":"2507.05660","title":"Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI","created":"2025-07-08","cited_by_count":0,"area":"alignment"},{"id":"2601.06157","title":"ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment","created":"2026-01-06","cited_by_count":0,"area":"alignment"},{"id":"2602.08377","title":"Reinforcement Learning with Backtracking Feedback","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"id":"2609.02215","title":"ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models","created":"2026-09-02","cited_by_count":0,"area":"alignment"}],"next_cursor":null}