{"total":89,"rows":[{"id":"2509.26346","title":"EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing","created":"2025-09-30","cited_by_count":62,"area":"alignment"},{"id":"2509.21500","title":"Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training","created":"2025-09-25","cited_by_count":53,"area":"alignment"},{"id":"2602.19313","title":"TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics","created":"2026-02-22","cited_by_count":33,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2512.24551","title":"PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation","created":"2025-12-31","cited_by_count":23,"area":"alignment"},{"id":"2602.01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","created":"2026-02-02","cited_by_count":21,"area":"alignment"},{"id":"2604.11626","title":"RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time","created":"2026-04-13","cited_by_count":14,"area":"alignment"},{"id":"2510.15859","title":"InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training","created":"2025-10-17","cited_by_count":12,"area":"alignment"},{"id":"2604.22891","title":"Quantifying and Mitigating Self-Preference Bias of LLM Judges","created":"2026-04-24","cited_by_count":10,"area":"alignment"},{"id":"2603.08091","title":"Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization","created":"2026-03-09","cited_by_count":9,"area":"alignment"},{"id":"2512.04784","title":"PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling","created":"2025-12-02","cited_by_count":7,"area":"alignment"},{"id":"2601.03868","title":"What Matters For Safety Alignment?","created":"2026-01-07","cited_by_count":7,"area":"alignment"},{"id":"2603.18736","title":"CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks","created":"2026-03-19","cited_by_count":7,"area":"alignment"},{"id":"2601.16403","title":"Towards a Theoretical Understanding to the Generalization of RLHF","created":"2026-01-23","cited_by_count":6,"area":"alignment"},{"id":"2603.20957","title":"Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models","created":"2026-03-21","cited_by_count":6,"area":"alignment"},{"id":"2606.19818","title":"Uncertainty-Aware Reward Modeling for Stable RLHF","created":"2026-06-18","cited_by_count":6,"area":"alignment"},{"id":"2510.00743","title":"From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling","created":"2025-10-01","cited_by_count":5,"area":"alignment"},{"id":"2510.06915","title":"LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling","created":"2025-10-08","cited_by_count":5,"area":"alignment"},{"id":"2511.19314","title":"PRInTS: Reward Modeling for Long-Horizon Information Seeking","created":"2025-11-24","cited_by_count":5,"area":"alignment"},{"id":"2603.00610","title":"CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction","created":"2026-02-28","cited_by_count":5,"area":"alignment"},{"id":"2605.29156","title":"RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains","created":"2026-05-27","cited_by_count":5,"area":"alignment"},{"id":"2511.16139","title":"Multidimensional Rubric-oriented Reward Model Learning via Geometric Projection Reference Constraints","created":"2025-11-20","cited_by_count":4,"area":"alignment"},{"id":"2511.21568","title":"RoParQ: Paraphrase-Aware Alignment of Large Language Models Towards Robustness to Paraphrased Questions","created":"2025-11-26","cited_by_count":4,"area":"alignment"},{"id":"2602.13891","title":"GSRM: Generative Speech Reward Model for Speech RLHF","created":"2026-02-14","cited_by_count":4,"area":"alignment"},{"id":"2603.09312","title":"IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework","created":"2026-03-10","cited_by_count":4,"area":"alignment"},{"id":"2603.14916","title":"EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing","created":"2026-03-16","cited_by_count":4,"area":"alignment"},{"id":"2510.00263","title":"Judging with Confidence: Calibrating Autoraters to Preference Distributions","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2510.21190","title":"The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning","created":"2025-10-24","cited_by_count":3,"area":"alignment"},{"id":"2601.19231","title":"LLMs Can Unlearn Refusal with Only 1,000 Benign Samples","created":"2026-01-27","cited_by_count":3,"area":"alignment"},{"id":"2602.24233","title":"Enhancing Spatial Understanding in Image Generation via Reward Modeling","created":"2026-02-27","cited_by_count":3,"area":"alignment"},{"id":"2603.13224","title":"Visual-ERM: Reward Modeling for Visual Equivalence","created":"2026-03-13","cited_by_count":3,"area":"alignment"},{"id":"2603.23184","title":"ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment","created":"2026-03-24","cited_by_count":3,"area":"alignment"},{"id":"2604.12710","title":"LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety","created":"2026-04-13","cited_by_count":3,"area":"alignment"},{"id":"2604.27093","title":"Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations","created":"2026-04-29","cited_by_count":3,"area":"alignment"},{"id":"2605.06036","title":"Optimal Transport for LLM Reward Modeling from Noisy Preference","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2605.14366","title":"Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax","created":"2026-05-14","cited_by_count":3,"area":"alignment"},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2510.07315","title":"SWE-IF: Aligning Code Evaluation with Human Preference","created":"2025-10-08","cited_by_count":2,"area":"alignment"},{"id":"2510.25799","title":"LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection","created":"2025-10-29","cited_by_count":2,"area":"alignment"},{"id":"2605.26158","title":"Furina: Fragmented Uncertainty-Driven Refusal Instability Attack","created":"2026-05-24","cited_by_count":2,"area":"alignment"},{"id":"2607.28609","title":"OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models","created":"2026-07-30","cited_by_count":2,"area":"alignment"},{"id":"2608.24794","title":"CAFE: Self-Improving Search Agents Need Co-Evolving Feedback","created":"2026-08-25","cited_by_count":2,"area":"alignment"},{"id":"2508.09463","title":"User-centric Subjective Leaderboard by Customizable Reward Modeling","created":"2025-08-13","cited_by_count":1,"area":"alignment"},{"id":"2510.02493","title":"Beyond Imitation: Recovering Dense Rewards from Demonstrations","created":"2025-10-02","cited_by_count":1,"area":"alignment"},{"id":"2511.18352","title":"MagicWand: A Universal Agent for Generation and Evaluation Aligned with User Preference","created":"2025-11-23","cited_by_count":1,"area":"alignment"},{"id":"2512.03568","title":"Synthetic Cognitive Walkthrough: Aligning Large Language Model Performance with Human Cognitive Walkthrough","created":"2025-12-03","cited_by_count":1,"area":"alignment"},{"id":"2602.00061","title":"Simple Role Assignment is Extraordinarily Effective for Safety Alignment","created":"2026-01-20","cited_by_count":1,"area":"alignment"},{"id":"2602.19919","title":"Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling","created":"2026-02-23","cited_by_count":1,"area":"alignment"},{"id":"2603.01163","title":"BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling","created":"2026-03-01","cited_by_count":1,"area":"alignment"},{"id":"2603.18528","title":"Correlation-Weighted Multi-Reward Optimization for Compositional Generation","created":"2026-03-19","cited_by_count":1,"area":"alignment"},{"id":"2604.00979","title":"Dual Optimal: Make Your LLM Peer-like with Dignity","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2604.16358","title":"SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics","created":"2026-03-18","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":"2604.20996","title":"AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models","created":"2026-04-22","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":"2605.07250","title":"Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment","created":"2026-05-08","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":"2607.24900","title":"Inverse RL Helps Align AI by Imitating Humans","created":"2026-07-27","cited_by_count":1,"area":"alignment"},{"id":"2608.02059","title":"MIEScore: Human-Aligned Evaluation for Multi-Source Image Editing","created":"2026-08-03","cited_by_count":1,"area":"alignment"},{"id":"2609.25270","title":"RULER: Instance-aware Rubric Rewards for SVG Generation","created":"2026-09-21","cited_by_count":1,"area":"alignment"},{"id":"2508.03990","title":"Are Today's LLMs Ready to Explain Well-Being Concepts?","created":"2025-08-06","cited_by_count":0,"area":"alignment"},{"id":"2508.05165","title":"Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models","created":"2025-08-07","cited_by_count":0,"area":"alignment"},{"id":"2511.19995","title":"CREward: A Type-Specific Creativity Reward Model","created":"2025-11-25","cited_by_count":0,"area":"alignment"},{"id":"2602.08819","title":"Bayesian Preference Learning for Test-Time Steerable Reward Models","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"id":"2604.10966","title":"You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass","created":"2026-04-13","cited_by_count":0,"area":"alignment"},{"id":"2604.25654","title":"Progressing beyond Art Masterpieces or Touristic Clich\\'es: how to assess your LLMs for cultural alignment?","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2605.08277","title":"Mitigating Many-shot Jailbreak Attacks with One Single Demonstration","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2605.17971","title":"Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling","created":"2026-05-18","cited_by_count":0,"area":"alignment"},{"id":"2605.20994","title":"Towards Context-Invariant Safety Alignment for Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2605.25876","title":"DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2605.27388","title":"Modeling Community Attitude through Reaction Tone: A Human-AI Collaborative Framework for Evaluating LLM Alignment with Linguistic Behaviors in Online Communities","created":"2026-04-12","cited_by_count":0,"area":"alignment"},{"id":"2606.00651","title":"MESA: Improving MoE Safety Alignment via Decentralized Expertise","created":"2026-05-30","cited_by_count":0,"area":"alignment"},{"id":"2606.03327","title":"CAPER: Clause-Aligned Process Supervision for Text-to-SQL","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2606.09635","title":"Gradient-Guided Reward Optimization for Inference-time Alignment","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2606.18961","title":"Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization","created":"2026-06-17","cited_by_count":0,"area":"alignment"},{"id":"2606.22652","title":"A Markov Chain Approach to Preference Alignment","created":"2026-06-21","cited_by_count":0,"area":"alignment"},{"id":"2606.28998","title":"Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2607.13315","title":"Meta-Learning Preferences for Multilingual LLM Alignment","created":"2026-07-14","cited_by_count":0,"area":"alignment"},{"id":"2607.13408","title":"Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models","created":"2026-07-15","cited_by_count":0,"area":"alignment"},{"id":"2607.23153","title":"In-Context Learning as Implicit Policy Gradient","created":"2026-07-25","cited_by_count":0,"area":"alignment"},{"id":"2607.28647","title":"ConnectED: A Curriculum-Aligned AI System for Vietnamese Instructional Lesson Planning and Student Learning","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2608.05040","title":"Private Direct Preference Optimization for LLM Alignment","created":"2026-08-05","cited_by_count":0,"area":"alignment"},{"id":"2608.09551","title":"Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.19598","title":"PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2608.26222","title":"NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2608.28593","title":"Statutory AI: Aligning Large Language Models With Legal Norms","created":"2026-06-13","cited_by_count":0,"area":"alignment"},{"id":"2609.29692","title":"Fair Like Us? Auditing LLM Alignment in Resource Allocation","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.34519","title":"EOPSA: Efficient On-Policy Self-Distilled Safety Alignment","created":"2026-09-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}