{"total":55,"rows":[{"id":"2510.07743","title":"OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment","created":"2025-10-09","cited_by_count":132,"area":"alignment"},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2512.16899","title":"Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image","created":"2025-12-18","cited_by_count":20,"area":"alignment"},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13,"area":"alignment"},{"id":"2506.12109","title":"Personalized LLM Decoding via Contrasting Personal Preference","created":"2025-06-13","cited_by_count":12,"area":"alignment"},{"id":"2602.02495","title":"Reward-free Alignment for Conflicting Objectives","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2506.16655","title":"Arch-Router: Aligning LLM Routing with Human Preferences","created":"2025-06-19","cited_by_count":9,"area":"alignment"},{"id":"2508.15811","title":"From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System","created":"2025-08-15","cited_by_count":9,"area":"alignment"},{"id":"2601.03868","title":"What Matters For Safety Alignment?","created":"2026-01-07","cited_by_count":7,"area":"alignment"},{"id":"2602.11328","title":"Evaluating Alignment of Behavioral Dispositions in LLMs","created":"2026-02-11","cited_by_count":7,"area":"alignment"},{"id":"2505.14185","title":"Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study","created":"2025-05-20","cited_by_count":6,"area":"alignment"},{"id":"2510.04320","title":"Read the Scene, Not the Script: Outcome-Aware Safety for LLMs","created":"2025-10-05","cited_by_count":6,"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":"2605.13062","title":"Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling","created":"2026-05-13","cited_by_count":6,"area":"alignment"},{"id":"2505.19731","title":"Proximal Point Nash Learning from Human Feedback","created":"2025-05-26","cited_by_count":5,"area":"alignment"},{"id":"2505.23950","title":"InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback","created":"2025-05-29","cited_by_count":4,"area":"alignment"},{"id":"2508.18569","title":"The Mind's Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation","created":"2025-08-26","cited_by_count":4,"area":"alignment"},{"id":"2508.16982","title":"Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens","created":"2025-08-23","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":"2510.07315","title":"SWE-IF: Aligning Code Evaluation with Human Preference","created":"2025-10-08","cited_by_count":2,"area":"alignment"},{"id":"2511.13290","title":"Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment","created":"2025-11-17","cited_by_count":2,"area":"alignment"},{"id":"2602.02383","title":"SLIME: Stabilized Likelihood Implicit Margin Enforcement for Preference Optimization","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":"2603.08104","title":"Invisible Safety Threat: Malicious Finetuning for LLM via Steganography","created":"2026-03-09","cited_by_count":2,"area":"alignment"},{"id":"2608.19802","title":"Stopping and Routing LLM Judge Panels","created":"2026-08-20","cited_by_count":2,"area":"alignment"},{"id":"2510.02493","title":"Beyond Imitation: Recovering Dense Rewards from Demonstrations","created":"2025-10-02","cited_by_count":1,"area":"alignment"},{"id":"2602.09533","title":"Autoregressive Direct Preference Optimization","created":"2026-02-10","cited_by_count":1,"area":"alignment"},{"id":"2602.19101","title":"Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models","created":"2026-02-22","cited_by_count":1,"area":"alignment"},{"id":"2604.11121","title":"BITS Pilani at SemEval-2026 Task 9: Structured Supervised Fine-Tuning with DPO Refinement for Polarization Detection","created":"2026-04-13","cited_by_count":1,"area":"alignment"},{"id":"2605.20408","title":"Spectral Souping: A Unified Framework for Online Preference Alignment","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2605.30619","title":"Reward Learning from Best-of-$N$ Preference Data: Targets, Tradeoffs, and Design Principles","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2510.05703","title":"Provably Convergent Primal-Dual DPO for Constrained LLM Alignment","created":"2025-10-07","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":"2512.05518","title":"Matching Ranks Over Probability Yields Truly Deep Safety Alignment","created":"2025-12-05","cited_by_count":0,"area":"alignment"},{"id":"2603.03536","title":"SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"id":"2604.25702","title":"Backtranslation Augmented Direct Preference Optimization for Neural Machine Translation","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2605.08878","title":"Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off","created":"2026-05-09","cited_by_count":0,"area":"alignment"},{"id":"2605.09225","title":"The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring","created":"2026-05-09","cited_by_count":0,"area":"alignment"},{"id":"2605.11632","title":"Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2605.13537","title":"Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"id":"2606.00369","title":"Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment","created":"2026-05-29","cited_by_count":0,"area":"alignment"},{"id":"2606.21645","title":"Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models","created":"2026-06-19","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":"2607.22766","title":"Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2608.20554","title":"aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy","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":"2608.29326","title":"StageWell: A Process-Aligned Chinese Corpus for Positive-Psychology Support Dialogue","created":"2026-08-29","cited_by_count":0,"area":"alignment"},{"id":"2609.02215","title":"ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models","created":"2026-09-02","cited_by_count":0,"area":"alignment"},{"id":"2609.03806","title":"SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.29781","title":"Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons","created":"2026-09-24","cited_by_count":0,"area":"alignment"},{"id":"2609.31855","title":"PHIRL: Aligning Learned Rewards with Task Progress for Inverse Reinforcement Learning","created":"2026-09-25","cited_by_count":0,"area":"alignment"},{"id":"2609.33086","title":"From Constitutions to Control: Interpretable Rewards for Aligning Language Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2610.01323","title":"TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety","created":"2026-10-01","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"}],"next_cursor":null}