{"total":38,"rows":[{"id":"2411.12882","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","created":"2024-11-19","cited_by_count":25,"area":"alignment"},{"id":"2508.03905","title":"Sotopia-RL: Reward Design for Social Intelligence","created":"2025-08-05","cited_by_count":24,"area":"alignment"},{"id":"2412.05210","title":"Evaluating and Aligning CodeLLMs on Human Preference","created":"2024-12-06","cited_by_count":22,"area":"alignment"},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"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":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15,"area":"alignment"},{"id":"2504.15804","title":"Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback","created":"2025-04-22","cited_by_count":14,"area":"alignment"},{"id":"2601.07349","title":"Reward Modeling from Natural Language Human Feedback","created":"2026-01-12","cited_by_count":11,"area":"alignment"},{"id":"2410.18585","title":"Aligning CodeLLMs with Direct Preference Optimization","created":"2024-10-24","cited_by_count":9,"area":"alignment"},{"id":"2411.13611","title":"DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs","created":"2024-11-20","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":"2502.16645","title":"CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale","created":"2025-02-23","cited_by_count":8,"area":"alignment"},{"id":"2510.08697","title":"BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution","created":"2025-10-09","cited_by_count":6,"area":"alignment"},{"id":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"id":"2601.04033","title":"Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model","created":"2026-01-07","cited_by_count":3,"area":"alignment"},{"id":"2505.12723","title":"On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding","created":"2025-05-19","cited_by_count":2,"area":"alignment"},{"id":"2505.18799","title":"ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models","created":"2025-05-24","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":"2602.01685","title":"Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment","created":"2026-02-02","cited_by_count":2,"area":"alignment"},{"id":"2602.16835","title":"NeST: Neuron Selective Tuning for LLM Safety","created":"2026-02-18","cited_by_count":2,"area":"alignment"},{"id":"2603.09400","title":"Reward Prediction with Factorized World States","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2605.11922","title":"StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning","created":"2026-05-12","cited_by_count":2,"area":"alignment"},{"id":"2505.22092","title":"VIRAL: Vision-grounded Integration for Reward design And Learning","created":"2025-05-28","cited_by_count":1,"area":"alignment"},{"id":"2507.20109","title":"Learning to Align Human Code Preferences","created":"2025-07-27","cited_by_count":1,"area":"alignment"},{"id":"2603.19987","title":"Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States","created":"2026-03-20","cited_by_count":1,"area":"alignment"},{"id":"2605.09134","title":"BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models","created":"2026-05-09","cited_by_count":1,"area":"alignment"},{"id":"2605.13536","title":"HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning","created":"2026-05-13","cited_by_count":1,"area":"alignment"},{"id":"2511.09880","title":"EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models","created":"2025-11-13","cited_by_count":0,"area":"alignment"},{"id":"2604.18327","title":"PARM: Pipeline-Adapted Reward Model","created":"2026-04-20","cited_by_count":0,"area":"alignment"},{"id":"2605.13229","title":"Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"id":"2606.20482","title":"Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users","created":"2026-06-18","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":"2608.05040","title":"Private Direct Preference Optimization for LLM Alignment","created":"2026-08-05","cited_by_count":0,"area":"alignment"},{"id":"2609.35109","title":"Using Context Is Not Enough: Test-Time Training for Personalized Reward Modeling","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.36849","title":"Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.12822","title":"Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems","created":"2026-10-09","cited_by_count":0,"area":"alignment"},{"id":"2610.18704","title":"Unlocking Token Rewards via Training-Free Reward Attribution","created":"2026-10-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}