{"total":46,"rows":[{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625,"area":"alignment"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"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":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148,"area":"alignment"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2402.01694","title":"ARGS: Alignment as Reward-Guided Search","created":"2024-01-23","cited_by_count":103,"area":"alignment"},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79,"area":"alignment"},{"id":"2402.06147","title":"DeAL: Decoding-time Alignment for Large Language Models","created":"2024-02-05","cited_by_count":55,"area":"alignment"},{"id":"2405.20495","title":"Transfer Q Star: Principled Decoding for LLM Alignment","created":"2024-05-30","cited_by_count":48,"area":"alignment"},{"id":"2507.00769","title":"LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing","created":"2025-07-01","cited_by_count":42,"area":"alignment"},{"id":"2503.17126","title":"Modifying Large Language Model Post-Training for Diverse Creative Writing","created":"2025-03-21","cited_by_count":40,"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":"2505.14442","title":"Creative Preference Optimization","created":"2025-05-20","cited_by_count":25,"area":"alignment"},{"id":"2412.10432","title":"Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection","created":"2024-12-11","cited_by_count":23,"area":"alignment"},{"id":"2311.09132","title":"Aligning Neural Machine Translation Models: Human Feedback in Training and Inference","created":"2023-11-15","cited_by_count":19,"area":"alignment"},{"id":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","cited_by_count":17,"area":"alignment"},{"id":"2210.07792","title":"Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning","created":"2022-10-14","cited_by_count":14,"area":"alignment"},{"id":"2406.11715","title":"Measuring memorization in RLHF for code completion","created":"2024-06-17","cited_by_count":13,"area":"alignment"},{"id":"2502.14289","title":"Drift: Decoding-time Personalized Alignments with Implicit User Preferences","created":"2025-02-20","cited_by_count":13,"area":"alignment"},{"id":"2406.07780","title":"A Critical Look At Tokenwise Reward-Guided Text Generation","created":"2024-06-12","cited_by_count":12,"area":"alignment"},{"id":"2405.17382","title":"ReMoDetect: Reward Models Recognize Aligned LLM's Generations","created":"2024-05-27","cited_by_count":11,"area":"alignment"},{"id":"2411.09661","title":"Adaptive Decoding via Latent Preference Optimization","created":"2024-11-14","cited_by_count":10,"area":"alignment"},{"id":"2406.18118","title":"SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance","created":"2024-06-26","cited_by_count":9,"area":"alignment"},{"id":"2403.14238","title":"Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection","created":"2024-03-21","cited_by_count":8,"area":"alignment"},{"id":"2407.16970","title":"Towards Aligning Language Models with Textual Feedback","created":"2024-07-24","cited_by_count":5,"area":"alignment"},{"id":"2409.17673","title":"Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization","created":"2024-09-26","cited_by_count":5,"area":"alignment"},{"id":"2502.04517","title":"Towards Cost-Effective Reward Guided Text Generation","created":"2025-02-06","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":"2411.07595","title":"Entropy Controllable Direct Preference Optimization","created":"2024-11-12","cited_by_count":4,"area":"alignment"},{"id":"2601.20687","title":"Positive-Unlabeled Reinforcement Learning Distillation for On-Premise Small Models","created":"2026-01-28","cited_by_count":4,"area":"alignment"},{"id":"2407.04615","title":"On the Low-Rank Parametrization of Reward Models for Controlled Language Generation","created":"2024-07-05","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":"2510.21883","title":"Language Ranker: A Lightweight Ranking framework for LLM Decoding","created":"2025-10-23","cited_by_count":2,"area":"alignment"},{"id":"2511.06942","title":"HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection","created":"2025-11-10","cited_by_count":1,"area":"alignment"},{"id":"2604.16923","title":"Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy","created":"2026-04-18","cited_by_count":1,"area":"alignment"},{"id":"2605.04831","title":"StoryAlign: Evaluating and Training Reward Models for Story Generation","created":"2026-05-06","cited_by_count":1,"area":"alignment"},{"id":"2605.28073","title":"StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative Enrichment","created":"2026-05-27","cited_by_count":1,"area":"alignment"},{"id":"2605.30021","title":"Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2406.10203","title":"A Probability--Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors","created":"2024-06-14","cited_by_count":0,"area":"alignment"},{"id":"2603.16410","title":"PlotTwist: A Creative Plot Generation Framework with Small Language Models","created":"2026-03-17","cited_by_count":0,"area":"alignment"},{"id":"2604.05517","title":"UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning","created":"2026-04-07","cited_by_count":0,"area":"alignment"},{"id":"2605.30526","title":"Measuring, Localizing, and Ablating Alignment Signatures in LLMs","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2607.20767","title":"Rushes: A Human Preference Dataset for Pluralistic Alignment","created":"2026-07-22","cited_by_count":0,"area":"alignment"},{"id":"2607.27366","title":"BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences","created":"2026-07-29","cited_by_count":0,"area":"alignment"},{"id":"2609.04824","title":"Generating Constructive Feedback on Stories via Reinforcement Learning","created":"2026-09-04","cited_by_count":0,"area":"alignment"}],"next_cursor":null}