{"total":97,"rows":[{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812,"area":"alignment"},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500,"area":"alignment"},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423,"area":"alignment"},{"id":"2306.17492","title":"Preference Ranking Optimization for Human Alignment","created":"2023-06-30","cited_by_count":285,"area":"alignment"},{"id":"2402.04792","title":"Direct Language Model Alignment from Online AI Feedback","created":"2024-02-07","cited_by_count":260,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2402.13228","title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","created":"2024-02-20","cited_by_count":241,"area":"alignment"},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135,"area":"alignment"},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2407.08639","title":"$\\beta$-DPO: Direct Preference Optimization with Dynamic $\\beta$","created":"2024-07-11","cited_by_count":90,"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":"2309.12053","title":"AceGPT, Localizing Large Language Models in Arabic","created":"2023-09-21","cited_by_count":75,"area":"alignment"},{"id":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"area":"alignment"},{"id":"2312.15997","title":"Aligning Large Language Models with Human Preferences through Representation Engineering","created":"2023-12-26","cited_by_count":71,"area":"alignment"},{"id":"2310.00212","title":"Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment","created":"2023-09-30","cited_by_count":57,"area":"alignment"},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"id":"2407.07880","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","created":"2024-07-10","cited_by_count":53,"area":"alignment"},{"id":"2404.02655","title":"Calibrating the Confidence of Large Language Models by Eliciting Fidelity","created":"2024-04-03","cited_by_count":47,"area":"alignment"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2511.07919","title":"Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison","created":"2025-11-11","cited_by_count":44,"area":"alignment"},{"id":"2406.14563","title":"Model Merging and Safety Alignment: One Bad Model Spoils the Bunch","created":"2024-06-20","cited_by_count":43,"area":"alignment"},{"id":"2309.00754","title":"Efficient RLHF: Reducing the Memory Usage of PPO","created":"2023-09-01","cited_by_count":40,"area":"alignment"},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39,"area":"alignment"},{"id":"2402.10958","title":"Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts","created":"2024-02-12","cited_by_count":36,"area":"alignment"},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35,"area":"alignment"},{"id":"2404.14723","title":"Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks","created":"2024-04-23","cited_by_count":35,"area":"alignment"},{"id":"2405.17888","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","created":"2024-05-28","cited_by_count":32,"area":"alignment"},{"id":"2410.12971","title":"Self-Pluralising Culture Alignment for Large Language Models","created":"2024-10-16","cited_by_count":31,"area":"alignment"},{"id":"2404.11049","title":"Stepwise Alignment for Constrained Language Model Policy Optimization","created":"2024-04-17","cited_by_count":30,"area":"alignment"},{"id":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28,"area":"alignment"},{"id":"2406.07739","title":"UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback","created":"2024-06-11","cited_by_count":27,"area":"alignment"},{"id":"2409.03650","title":"On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization","created":"2024-09-05","cited_by_count":27,"area":"alignment"},{"id":"2401.06785","title":"Human-Instruction-Free LLM Self-Alignment with Limited Samples","created":"2024-01-06","cited_by_count":25,"area":"alignment"},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25,"area":"alignment"},{"id":"2505.14442","title":"Creative Preference Optimization","created":"2025-05-20","cited_by_count":25,"area":"alignment"},{"id":"2503.10990","title":"Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium","created":"2025-03-14","cited_by_count":23,"area":"alignment"},{"id":"2507.01915","title":"Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models","created":"2025-07-02","cited_by_count":23,"area":"alignment"},{"id":"2407.07342","title":"Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture","created":"2024-07-10","cited_by_count":22,"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":"2402.05000","title":"Pedagogical Alignment of Large Language Models","created":"2024-02-07","cited_by_count":19,"area":"alignment"},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2405.08154","title":"LLM Theory of Mind and Alignment: Opportunities and Risks","created":"2024-05-13","cited_by_count":18,"area":"alignment"},{"id":"2403.00199","title":"Improving Socratic Question Generation using Data Augmentation and Preference Optimization","created":"2024-03-01","cited_by_count":16,"area":"alignment"},{"id":"2404.04102","title":"ROPO: Robust Preference Optimization for Large Language Models","created":"2024-04-05","cited_by_count":16,"area":"alignment"},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2503.09925","title":"PluralLLM: Pluralistic Alignment in LLMs via Federated Learning","created":"2025-03-13","cited_by_count":14,"area":"alignment"},{"id":"2310.16271","title":"CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment","created":"2023-10-25","cited_by_count":13,"area":"alignment"},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2505.05465","title":"ComPO: Preference Alignment via Comparison Oracles","created":"2025-05-08","cited_by_count":13,"area":"alignment"},{"id":"2509.01418","title":"On the Alignment of Large Language Models with Global Human Opinion","created":"2025-09-01","cited_by_count":13,"area":"alignment"},{"id":"2602.02495","title":"Reward-free Alignment for Conflicting Objectives","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2505.20627","title":"Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching","created":"2025-05-27","cited_by_count":10,"area":"alignment"},{"id":"2506.18931","title":"Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs","created":"2025-06-21","cited_by_count":10,"area":"alignment"},{"id":"2310.06450","title":"Constructive Large Language Models Alignment with Diverse Feedback","created":"2023-10-10","cited_by_count":9,"area":"alignment"},{"id":"2406.07168","title":"Teaching Language Models to Self-Improve by Learning from Language Feedback","created":"2024-06-11","cited_by_count":9,"area":"alignment"},{"id":"2502.16825","title":"Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization","created":"2025-02-24","cited_by_count":9,"area":"alignment"},{"id":"2507.21983","title":"Improving Generative Ad Text on Facebook using Reinforcement Learning","created":"2025-07-29","cited_by_count":9,"area":"alignment"},{"id":"2305.06176","title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling","created":"2023-05-09","cited_by_count":8,"area":"alignment"},{"id":"2408.10701","title":"Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique","created":"2024-08-20","cited_by_count":8,"area":"alignment"},{"id":"2502.03095","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms","created":"2025-02-05","cited_by_count":8,"area":"alignment"},{"id":"2310.00898","title":"Enabling Language Models to Implicitly Learn Self-Improvement","created":"2023-10-02","cited_by_count":7,"area":"alignment"},{"id":"2506.12350","title":"Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory","created":"2025-06-14","cited_by_count":7,"area":"alignment"},{"id":"2305.02531","title":"Can LLMs Capture Human Preferences?","created":"2023-05-04","cited_by_count":6,"area":"alignment"},{"id":"2309.02884","title":"Aligning Large Language Models for Clinical Tasks","created":"2023-09-06","cited_by_count":6,"area":"alignment"},{"id":"2409.20053","title":"GUNDAM: Aligning Large Language Models with Graph Understanding","created":"2024-09-30","cited_by_count":5,"area":"alignment"},{"id":"2410.06293","title":"Accelerated Preference Optimization for Large Language Model Alignment","created":"2024-10-08","cited_by_count":5,"area":"alignment"},{"id":"2312.16430","title":"Preference as Reward, Maximum Preference Optimization with Importance Sampling","created":"2023-12-27","cited_by_count":4,"area":"alignment"},{"id":"2503.07426","title":"RePO: Understanding Preference Learning Through ReLU-Based Optimization","created":"2025-03-10","cited_by_count":4,"area":"alignment"},{"id":"2503.20194","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2510.06652","title":"Aligning Large Language Models via Fully Self-Synthetic Data","created":"2025-10-08","cited_by_count":4,"area":"alignment"},{"id":"2602.11523","title":"Unifying Stable Optimization and Reference Regularization in RLHF","created":"2026-02-12","cited_by_count":4,"area":"alignment"},{"id":"2403.16649","title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","created":"2024-03-25","cited_by_count":3,"area":"alignment"},{"id":"2404.12195","title":"OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data","created":"2024-04-18","cited_by_count":3,"area":"alignment"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2408.12799","title":"Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora","created":"2024-08-23","cited_by_count":3,"area":"alignment"},{"id":"2410.20298","title":"Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data","created":"2024-10-27","cited_by_count":3,"area":"alignment"},{"id":"2509.13869","title":"Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs","created":"2025-09-17","cited_by_count":3,"area":"alignment"},{"id":"2406.12416","title":"Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models","created":"2024-06-18","cited_by_count":2,"area":"alignment"},{"id":"2505.23923","title":"Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity","created":"2025-05-29","cited_by_count":2,"area":"alignment"},{"id":"2507.20067","title":"PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training","created":"2025-07-26","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":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2509.25148","title":"AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models","created":"2025-09-29","cited_by_count":1,"area":"alignment"},{"id":"2403.02745","title":"CURATRON: Complete and Robust Preference Data for Rigorous Alignment of Large Language Models","created":"2024-03-05","cited_by_count":0,"area":"alignment"},{"id":"2509.12179","title":"Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation","created":"2025-09-15","cited_by_count":0,"area":"alignment"},{"id":"2510.05534","title":"Revisiting Self-Play Preference Optimization: On the Role of Prompt Difficulty","created":"2025-10-07","cited_by_count":0,"area":"alignment"},{"id":"2604.01787","title":"DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment","created":"2026-04-02","cited_by_count":0,"area":"alignment"},{"id":"2604.01837","title":"PLOT: Enhancing Preference Learning via Optimal Transport","created":"2026-04-02","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":"2608.13069","title":"Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds","created":"2026-08-13","cited_by_count":0,"area":"alignment"},{"id":"2609.19144","title":"A Zeroth-Order Paradigm for LLM Preference Alignment","created":"2026-09-16","cited_by_count":0,"area":"alignment"}],"next_cursor":null}