{"total":140,"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":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785,"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":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2311.10702","title":"Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2","created":"2023-11-17","cited_by_count":229,"area":"alignment"},{"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":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195,"area":"alignment"},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2406.00045","title":"Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization","created":"2024-05-28","cited_by_count":118,"area":"alignment"},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115,"area":"alignment"},{"id":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","cited_by_count":111,"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":"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":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2402.05369","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","created":"2024-02-08","cited_by_count":85,"area":"alignment"},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"area":"alignment"},{"id":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57,"area":"alignment"},{"id":"2310.05910","title":"SALMON: Self-Alignment with Instructable Reward Models","created":"2023-10-09","cited_by_count":55,"area":"alignment"},{"id":"2402.10038","title":"RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models","created":"2024-02-15","cited_by_count":48,"area":"alignment"},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2402.05699","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","created":"2024-02-08","cited_by_count":46,"area":"alignment"},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2403.14221","title":"Improving the Robustness of Large Language Models via Consistency Alignment","created":"2024-03-21","cited_by_count":36,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2307.12966","title":"Aligning Large Language Models with Human: A Survey","created":"2023-07-24","cited_by_count":32,"area":"alignment"},{"id":"2406.16235","title":"Preference Tuning For Toxicity Mitigation Generalizes Across Languages","created":"2024-06-23","cited_by_count":31,"area":"alignment"},{"id":"2406.07739","title":"UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback","created":"2024-06-11","cited_by_count":27,"area":"alignment"},{"id":"2310.01581","title":"On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?","created":"2023-10-02","cited_by_count":26,"area":"alignment"},{"id":"2504.07532","title":"AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation","created":"2025-04-10","cited_by_count":25,"area":"alignment"},{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25,"area":"alignment"},{"id":"2410.13116","title":"Learning to Summarize from LLM-generated Feedback","created":"2024-10-17","cited_by_count":24,"area":"alignment"},{"id":"2508.03905","title":"Sotopia-RL: Reward Design for Social Intelligence","created":"2025-08-05","cited_by_count":24,"area":"alignment"},{"id":"2507.05129","title":"SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction","created":"2025-07-07","cited_by_count":23,"area":"alignment"},{"id":"2311.02775","title":"AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs","created":"2023-11-05","cited_by_count":22,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2406.13925","title":"GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models","created":"2024-06-20","cited_by_count":18,"area":"alignment"},{"id":"2405.07101","title":"Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA","created":"2024-05-11","cited_by_count":17,"area":"alignment"},{"id":"2410.18027","title":"Cross-lingual Transfer of Reward Models in Multilingual Alignment","created":"2024-10-23","cited_by_count":17,"area":"alignment"},{"id":"2410.18469","title":"Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities","created":"2024-10-24","cited_by_count":17,"area":"alignment"},{"id":"2403.00199","title":"Improving Socratic Question Generation using Data Augmentation and Preference Optimization","created":"2024-03-01","cited_by_count":16,"area":"alignment"},{"id":"2406.04879","title":"A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques","created":"2024-06-07","cited_by_count":16,"area":"alignment"},{"id":"2406.10991","title":"Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers","created":"2024-06-16","cited_by_count":15,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2506.14681","title":"Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality","created":"2025-06-17","cited_by_count":14,"area":"alignment"},{"id":"2410.01532","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","created":"2024-10-02","cited_by_count":12,"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":"2312.07876","title":"Causality Analysis for Evaluating the Security of Large Language Models","created":"2023-12-13","cited_by_count":11,"area":"alignment"},{"id":"2404.00486","title":"Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs","created":"2024-03-30","cited_by_count":11,"area":"alignment"},{"id":"2403.09704","title":"Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations","created":"2024-03-08","cited_by_count":10,"area":"alignment"},{"id":"2406.15352","title":"A SMART Mnemonic Sounds like \"Glue Tonic\": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick","created":"2024-06-21","cited_by_count":10,"area":"alignment"},{"id":"2412.19436","title":"Low-Rank Contextual Reinforcement Learning from Heterogeneous Human Feedback","created":"2024-12-27","cited_by_count":10,"area":"alignment"},{"id":"2307.10512","title":"IvyGPT: InteractiVe Chinese pathwaY language model in medical domain","created":"2023-07-20","cited_by_count":9,"area":"alignment"},{"id":"2407.03051","title":"Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment","created":"2024-07-03","cited_by_count":9,"area":"alignment"},{"id":"2409.19715","title":"Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code","created":"2024-09-29","cited_by_count":9,"area":"alignment"},{"id":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2510.14301","title":"A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space","created":"2025-10-16","cited_by_count":9,"area":"alignment"},{"id":"2311.07723","title":"Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains","created":"2023-11-13","cited_by_count":8,"area":"alignment"},{"id":"2406.16743","title":"Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions","created":"2024-06-24","cited_by_count":8,"area":"alignment"},{"id":"2402.02479","title":"BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback","created":"2024-02-04","cited_by_count":7,"area":"alignment"},{"id":"2406.12606","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","created":"2024-06-18","cited_by_count":7,"area":"alignment"},{"id":"2409.00935","title":"Self-Judge: Selective Instruction Following with Alignment Self-Evaluation","created":"2024-09-02","cited_by_count":7,"area":"alignment"},{"id":"2409.18618","title":"Model-based Preference Optimization in Abstractive Summarization without Human Feedback","created":"2024-09-27","cited_by_count":7,"area":"alignment"},{"id":"2603.00025","title":"TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation","created":"2026-02-03","cited_by_count":7,"area":"alignment"},{"id":"2407.00693","title":"BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization","created":"2024-06-30","cited_by_count":6,"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":"2504.21053","title":"NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models","created":"2025-04-29","cited_by_count":6,"area":"alignment"},{"id":"2605.01123","title":"PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"id":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2404.16020","title":"Investigating Adversarial Trigger Transfer in Large Language Models","created":"2024-04-24","cited_by_count":5,"area":"alignment"},{"id":"2410.08458","title":"Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both","created":"2024-10-11","cited_by_count":5,"area":"alignment"},{"id":"2410.10392","title":"Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search","created":"2024-10-14","cited_by_count":5,"area":"alignment"},{"id":"2403.04187","title":"Preference optimization of protein language models as a multi-objective binder design paradigm","created":"2024-03-07","cited_by_count":4,"area":"alignment"},{"id":"2407.03232","title":"Single Character Perturbations Break LLM Alignment","created":"2024-07-03","cited_by_count":4,"area":"alignment"},{"id":"2412.10689","title":"Learning to Verify Summary Facts with Fine-Grained LLM Feedback","created":"2024-12-14","cited_by_count":4,"area":"alignment"},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2505.14607","title":"sudoLLM: On Multi-role Alignment of Language Models","created":"2025-05-20","cited_by_count":4,"area":"alignment"},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","cited_by_count":4,"area":"alignment"},{"id":"2602.09411","title":"K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge","created":"2026-02-10","cited_by_count":4,"area":"alignment"},{"id":"2605.00195","title":"Diversity in Large Language Models under Supervised Fine-Tuning","created":"2026-04-30","cited_by_count":4,"area":"alignment"},{"id":"2605.04266","title":"Explaining and Preventing Alignment Collapse in Iterative RLHF","created":"2026-05-05","cited_by_count":4,"area":"alignment"},{"id":"2404.12195","title":"OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data","created":"2024-04-18","cited_by_count":3,"area":"alignment"},{"id":"2405.08619","title":"ALMol: Aligned Language-Molecule Translation LLMs through Offline Preference Contrastive Optimisation","created":"2024-05-14","cited_by_count":3,"area":"alignment"},{"id":"2503.10927","title":"OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses","created":"2025-03-13","cited_by_count":3,"area":"alignment"},{"id":"2509.13869","title":"Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs","created":"2025-09-17","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":"2607.25614","title":"MemSFT: Mitigating Alignment Tax with an External Parametric Memory","created":"2026-07-28","cited_by_count":3,"area":"alignment"},{"id":"2410.18127","title":"Holistic Utility Preference Learning for Listwise Alignment","created":"2024-10-17","cited_by_count":2,"area":"alignment"},{"id":"2412.00074","title":"Safe to Serve: Aligning Instruction-Tuned Models for Safety and Helpfulness","created":"2024-11-26","cited_by_count":2,"area":"alignment"},{"id":"2504.08590","title":"Playpen: An Environment for Exploring Learning Through Conversational Interaction","created":"2025-04-11","cited_by_count":2,"area":"alignment"},{"id":"2511.19523","title":"EAGER: Edge-Aligned LLM Defense for Robust, Efficient, and Accurate Cybersecurity Question Answering","created":"2025-11-24","cited_by_count":2,"area":"alignment"},{"id":"2604.18239","title":"Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner","created":"2026-04-20","cited_by_count":2,"area":"alignment"},{"id":"2401.10580","title":"PHOENIX: Open-Source Language Adaption for Direct Preference Optimization","created":"2024-01-19","cited_by_count":1,"area":"alignment"},{"id":"2407.17546","title":"Exploring Domain Robust Lightweight Reward Models based on Router Mechanism","created":"2024-07-24","cited_by_count":1,"area":"alignment"},{"id":"2510.17652","title":"Qomhra: A Bilingual Irish and English Large Language Model","created":"2025-10-20","cited_by_count":1,"area":"alignment"},{"id":"2510.19265","title":"Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2602.16438","title":"Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignment","created":"2026-02-18","cited_by_count":1,"area":"alignment"},{"id":"2603.13776","title":"Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion","created":"2026-03-14","cited_by_count":1,"area":"alignment"}],"next_cursor":"100"}