{"total":43,"rows":[{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360,"area":"alignment"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2305.15075","title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","created":"2023-05-24","cited_by_count":214,"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":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148,"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":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136,"area":"alignment"},{"id":"2401.18058","title":"LongAlign: A Recipe for Long Context Alignment of Large Language Models","created":"2024-01-31","cited_by_count":106,"area":"alignment"},{"id":"2403.05612","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","created":"2024-03-08","cited_by_count":87,"area":"alignment"},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2307.05532","title":"Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators","created":"2023-07-08","cited_by_count":56,"area":"alignment"},{"id":"2406.19371","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","created":"2024-06-27","cited_by_count":34,"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":"2409.08813","title":"Your Weak LLM is Secretly a Strong Teacher for Alignment","created":"2024-09-13","cited_by_count":20,"area":"alignment"},{"id":"2508.08746","title":"Interpretable Reward Model via Sparse Autoencoder","created":"2025-08-12","cited_by_count":18,"area":"alignment"},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13,"area":"alignment"},{"id":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"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":"2606.24993","title":"The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order","created":"2026-06-23","cited_by_count":9,"area":"alignment"},{"id":"2412.03253","title":"Alignment at Pre-training! Towards Native Alignment for Arabic LLMs","created":"2024-12-04","cited_by_count":7,"area":"alignment"},{"id":"2604.08524","title":"What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal","created":"2026-04-09","cited_by_count":7,"area":"alignment"},{"id":"2211.05750","title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control","created":"2022-11-10","cited_by_count":6,"area":"alignment"},{"id":"2504.14452","title":"ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data","created":"2025-04-20","cited_by_count":6,"area":"alignment"},{"id":"2507.00665","title":"SAFER: Probing Safety in Reward Models with Sparse Autoencoder","created":"2025-07-01","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":"2506.03968","title":"From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding","created":"2025-06-04","cited_by_count":5,"area":"alignment"},{"id":"2507.02332","title":"PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage","created":"2025-07-03","cited_by_count":5,"area":"alignment"},{"id":"2510.08075","title":"Multi-Condition Conformal Selection","created":"2025-10-09","cited_by_count":4,"area":"alignment"},{"id":"2604.12384","title":"Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints","created":"2026-04-14","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":"2311.08487","title":"Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective","created":"2023-11-14","cited_by_count":3,"area":"alignment"},{"id":"2509.17276","title":"Probabilistic Token Alignment for Large Language Model Fusion","created":"2025-09-21","cited_by_count":3,"area":"alignment"},{"id":"2605.08513","title":"A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models","created":"2026-05-08","cited_by_count":3,"area":"alignment"},{"id":"2606.01196","title":"Low-Resource Safety Failures Are Action Failures, Not Representation Failures","created":"2026-05-31","cited_by_count":2,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2605.25759","title":"Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences","created":"2026-05-25","cited_by_count":1,"area":"alignment"},{"id":"2509.07642","title":"Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment","created":"2025-09-09","cited_by_count":0,"area":"alignment"},{"id":"2601.17096","title":"Beyond Instrumental and Substitutive Paradigms: Introducing Machine Culture as an Emergent Phenomenon in Large Language Models","created":"2026-01-23","cited_by_count":0,"area":"alignment"},{"id":"2603.16622","title":"Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target Model","created":"2026-03-17","cited_by_count":0,"area":"alignment"},{"id":"2605.28826","title":"From Context Shift to Stylistic Collapse: Why Training Objectives Matter More Than Scale","created":"2026-04-08","cited_by_count":0,"area":"alignment"},{"id":"2606.29581","title":"The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis","created":"2026-06-28","cited_by_count":0,"area":"alignment"},{"id":"2608.29936","title":"When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs","created":"2026-08-30","cited_by_count":0,"area":"alignment"}],"next_cursor":null}