{"total":98,"rows":[{"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":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100,"area":"alignment"},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"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":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406,"area":"alignment"},{"id":"2312.15685","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","created":"2023-12-25","cited_by_count":364,"area":"alignment"},{"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":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2309.07124","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","created":"2023-09-13","cited_by_count":157,"area":"alignment"},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122,"area":"alignment"},{"id":"2308.03549","title":"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue","created":"2023-08-07","cited_by_count":119,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"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":"2305.13735","title":"Aligning Large Language Models through Synthetic Feedback","created":"2023-05-23","cited_by_count":75,"area":"alignment"},{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74,"area":"alignment"},{"id":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68,"area":"alignment"},{"id":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63,"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":"2406.09760","title":"Bootstrapping Language Models with DPO Implicit Rewards","created":"2024-06-14","cited_by_count":53,"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":"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":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2307.12950","title":"RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment","created":"2023-07-24","cited_by_count":43,"area":"alignment"},{"id":"2306.10968","title":"BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models","created":"2023-06-19","cited_by_count":42,"area":"alignment"},{"id":"2311.04072","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","created":"2023-11-07","cited_by_count":35,"area":"alignment"},{"id":"2402.15062","title":"Don't Just Say \"I don't know\"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations","created":"2024-02-23","cited_by_count":30,"area":"alignment"},{"id":"2405.17931","title":"Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment","created":"2024-05-28","cited_by_count":28,"area":"alignment"},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28,"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":"2401.06785","title":"Human-Instruction-Free LLM Self-Alignment with Limited Samples","created":"2024-01-06","cited_by_count":25,"area":"alignment"},{"id":"2401.11458","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","created":"2024-01-21","cited_by_count":25,"area":"alignment"},{"id":"2403.19443","title":"Mixed Preference Optimization: Reinforcement Learning with Data Selection and Better Reference Model","created":"2024-03-28","cited_by_count":25,"area":"alignment"},{"id":"2305.17608","title":"Reward Collapse in Aligning Large Language Models","created":"2023-05-28","cited_by_count":24,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2312.15907","title":"Align on the Fly: Adapting Chatbot Behavior to Established Norms","created":"2023-12-26","cited_by_count":23,"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":"2405.12739","title":"SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling","created":"2024-05-21","cited_by_count":21,"area":"alignment"},{"id":"2411.00062","title":"Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play","created":"2024-10-31","cited_by_count":21,"area":"alignment"},{"id":"2402.10893","title":"RLVF: Learning from Verbal Feedback without Overgeneralization","created":"2024-02-16","cited_by_count":19,"area":"alignment"},{"id":"2404.14313","title":"Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels","created":"2024-04-22","cited_by_count":19,"area":"alignment"},{"id":"2408.16482","title":"Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning","created":"2024-08-29","cited_by_count":19,"area":"alignment"},{"id":"2402.17358","title":"SoFA: Shielded On-the-fly Alignment via Priority Rule Following","created":"2024-02-27","cited_by_count":18,"area":"alignment"},{"id":"2405.19744","title":"X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions","created":"2024-05-30","cited_by_count":18,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2406.10630","title":"Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models","created":"2024-06-15","cited_by_count":18,"area":"alignment"},{"id":"2502.09723","title":"QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language","created":"2025-02-13","cited_by_count":18,"area":"alignment"},{"id":"2411.08733","title":"Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models","created":"2024-11-13","cited_by_count":13,"area":"alignment"},{"id":"2410.15483","title":"Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective","created":"2024-10-20","cited_by_count":12,"area":"alignment"},{"id":"2403.03419","title":"Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization","created":"2024-03-06","cited_by_count":11,"area":"alignment"},{"id":"2403.18341","title":"IterAlign: Iterative Constitutional Alignment of Large Language Models","created":"2024-03-27","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":"2305.11952","title":"Self-QA: Unsupervised Knowledge Guided Language Model Alignment","created":"2023-05-19","cited_by_count":9,"area":"alignment"},{"id":"2407.16008","title":"Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation","created":"2024-07-22","cited_by_count":9,"area":"alignment"},{"id":"2410.06491","title":"Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack","created":"2024-10-09","cited_by_count":8,"area":"alignment"},{"id":"2502.13417","title":"RLTHF: Targeted Human Feedback for LLM Alignment","created":"2025-02-19","cited_by_count":8,"area":"alignment"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2310.00898","title":"Enabling Language Models to Implicitly Learn Self-Improvement","created":"2023-10-02","cited_by_count":7,"area":"alignment"},{"id":"2405.21040","title":"Direct Alignment of Language Models via Quality-Aware Self-Refinement","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2408.03618","title":"A Logical Fallacy-Informed Framework for Argument Generation","created":"2024-08-07","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":"2504.12083","title":"Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization","created":"2025-04-16","cited_by_count":7,"area":"alignment"},{"id":"2312.02206","title":"Axiomatic Preference Modeling for Longform Question Answering","created":"2023-12-02","cited_by_count":6,"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":"2502.03397","title":"SPRI: Aligning Large Language Models with Context-Situated Principles","created":"2025-02-05","cited_by_count":5,"area":"alignment"},{"id":"2310.00819","title":"Parameter-Efficient Tuning Helps Language Model Alignment","created":"2023-10-01","cited_by_count":4,"area":"alignment"},{"id":"2402.01706","title":"MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds","created":"2024-01-25","cited_by_count":4,"area":"alignment"},{"id":"2404.00604","title":"Extensive Self-Contrast Enables Feedback-Free Language Model Alignment","created":"2024-03-31","cited_by_count":4,"area":"alignment"},{"id":"2406.03642","title":"Is Free Self-Alignment Possible?","created":"2024-06-05","cited_by_count":4,"area":"alignment"},{"id":"2406.08842","title":"ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions","created":"2024-06-13","cited_by_count":4,"area":"alignment"},{"id":"2406.12182","title":"Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models","created":"2024-06-18","cited_by_count":4,"area":"alignment"},{"id":"2408.10392","title":"Value Alignment from Unstructured Text","created":"2024-08-19","cited_by_count":4,"area":"alignment"},{"id":"2408.12163","title":"Preference-Guided Reflective Sampling for Aligning Language Models","created":"2024-08-22","cited_by_count":4,"area":"alignment"},{"id":"2501.17112","title":"Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AI","created":"2025-01-28","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":"2606.24014","title":"Reinforcement Learning Towards Broadly and Persistently Beneficial Models","created":"2026-06-22","cited_by_count":4,"area":"alignment"},{"id":"2502.08657","title":"Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions","created":"2025-02-08","cited_by_count":3,"area":"alignment"},{"id":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","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":"2511.06222","title":"SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization","created":"2025-11-09","cited_by_count":3,"area":"alignment"},{"id":"2605.02971","title":"Multilingual Safety Alignment via Self-Distillation","created":"2026-05-03","cited_by_count":3,"area":"alignment"},{"id":"2406.10813","title":"Self-Evolution Fine-Tuning for Policy Optimization","created":"2024-06-16","cited_by_count":2,"area":"alignment"},{"id":"2410.12194","title":"Negative-Prompt-driven Alignment for Generative Language Model","created":"2024-10-16","cited_by_count":2,"area":"alignment"},{"id":"2505.23114","title":"Alignment Data Map for Efficient Preference Data Selection and Diagnosis","created":"2025-05-29","cited_by_count":2,"area":"alignment"},{"id":"2507.08020","title":"Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation","created":"2025-07-08","cited_by_count":2,"area":"alignment"},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2604.19024","title":"Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback","created":"2026-04-21","cited_by_count":2,"area":"alignment"},{"id":"2408.02599","title":"Progressively Label Enhancement for Large Language Model Alignment","created":"2024-08-05","cited_by_count":1,"area":"alignment"},{"id":"2505.19700","title":"Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2507.17477","title":"An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models","created":"2025-07-23","cited_by_count":1,"area":"alignment"},{"id":"2510.06670","title":"PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch","created":"2025-10-08","cited_by_count":1,"area":"alignment"},{"id":"2511.02356","title":"ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs","created":"2025-11-04","cited_by_count":1,"area":"alignment"},{"id":"2512.05464","title":"Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment","created":"2025-12-05","cited_by_count":1,"area":"alignment"},{"id":"2406.14208","title":"SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots","created":"2024-06-20","cited_by_count":0,"area":"alignment"},{"id":"2511.13007","title":"GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs","created":"2025-11-17","cited_by_count":0,"area":"alignment"},{"id":"2604.07754","title":"The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training","created":"2026-04-09","cited_by_count":0,"area":"alignment"},{"id":"2608.21969","title":"ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents","created":"2026-08-22","cited_by_count":0,"area":"alignment"}],"next_cursor":null}