{"total":83,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104,"area":"alignment"},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134,"area":"alignment"},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"area":"alignment"},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78,"area":"alignment"},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"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":"2310.19677","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","created":"2023-10-30","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":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29,"area":"alignment"},{"id":"2310.05782","title":"Aligning Language Models with Human Preferences via a Bayesian Approach","created":"2023-10-09","cited_by_count":27,"area":"alignment"},{"id":"2408.15313","title":"Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models","created":"2024-08-27","cited_by_count":27,"area":"alignment"},{"id":"2402.18120","title":"Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?","created":"2024-02-28","cited_by_count":24,"area":"alignment"},{"id":"2508.03905","title":"Sotopia-RL: Reward Design for Social Intelligence","created":"2025-08-05","cited_by_count":24,"area":"alignment"},{"id":"2501.14940","title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","created":"2025-01-24","cited_by_count":20,"area":"alignment"},{"id":"2405.07101","title":"Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA","created":"2024-05-11","cited_by_count":17,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2506.14681","title":"Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality","created":"2025-06-17","cited_by_count":14,"area":"alignment"},{"id":"2210.07652","title":"Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values","created":"2022-10-14","cited_by_count":13,"area":"alignment"},{"id":"2406.10977","title":"Toward Optimal LLM Alignments Using Two-Player Games","created":"2024-06-16","cited_by_count":13,"area":"alignment"},{"id":"2407.16637","title":"Course-Correction: Safety Alignment Using Synthetic Preferences","created":"2024-07-23","cited_by_count":13,"area":"alignment"},{"id":"2410.07304","title":"The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making","created":"2024-10-09","cited_by_count":12,"area":"alignment"},{"id":"2411.11937","title":"Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets","created":"2024-11-18","cited_by_count":11,"area":"alignment"},{"id":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10,"area":"alignment"},{"id":"2403.12805","title":"Contextual Moral Value Alignment Through Context-Based Aggregation","created":"2024-03-19","cited_by_count":10,"area":"alignment"},{"id":"2406.16316","title":"Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?","created":"2024-06-24","cited_by_count":10,"area":"alignment"},{"id":"2404.18870","title":"More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness","created":"2024-04-29","cited_by_count":9,"area":"alignment"},{"id":"2502.00313","title":"Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values","created":"2025-02-01","cited_by_count":9,"area":"alignment"},{"id":"2506.04721","title":"SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat","created":"2025-06-05","cited_by_count":9,"area":"alignment"},{"id":"2311.07723","title":"Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains","created":"2023-11-13","cited_by_count":8,"area":"alignment"},{"id":"2407.03856","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","created":"2024-07-04","cited_by_count":7,"area":"alignment"},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"area":"alignment"},{"id":"2510.23751","title":"Debiasing Reward Models by Representation Learning with Guarantees","created":"2025-10-27","cited_by_count":6,"area":"alignment"},{"id":"2511.02109","title":"Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences","created":"2025-11-03","cited_by_count":6,"area":"alignment"},{"id":"2511.10032","title":"Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedback","created":"2025-11-13","cited_by_count":6,"area":"alignment"},{"id":"2603.01907","title":"Efficient RLVR Training via Weighted Mutual Information Data Selection","created":"2026-03-02","cited_by_count":6,"area":"alignment"},{"id":"2301.03740","title":"A Multi-Level Framework for the AI Alignment Problem","created":"2023-01-10","cited_by_count":5,"area":"alignment"},{"id":"2411.11853","title":"Chat Bankman-Fried: an Exploration of LLM Alignment in Finance","created":"2024-11-01","cited_by_count":5,"area":"alignment"},{"id":"2509.05381","title":"Murphys Laws of AI Alignment: Why the Gap Always Wins","created":"2025-09-04","cited_by_count":5,"area":"alignment"},{"id":"2509.15090","title":"Emergent Alignment via Competition","created":"2025-09-18","cited_by_count":5,"area":"alignment"},{"id":"2408.10392","title":"Value Alignment from Unstructured Text","created":"2024-08-19","cited_by_count":4,"area":"alignment"},{"id":"2501.17117","title":"Histoires Morales: A French Dataset for Assessing Moral Alignment","created":"2025-01-28","cited_by_count":4,"area":"alignment"},{"id":"2405.13541","title":"Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts","created":"2024-05-22","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":"2506.01495","title":"C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models","created":"2025-06-02","cited_by_count":3,"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":"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":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2605.27851","title":"When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models","created":"2026-05-27","cited_by_count":3,"area":"alignment"},{"id":"2406.06587","title":"TouchAI: Exploring human-AI perceptual alignment in touch through language model representations","created":"2024-06-05","cited_by_count":2,"area":"alignment"},{"id":"2408.07663","title":"Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions","created":"2024-08-14","cited_by_count":2,"area":"alignment"},{"id":"2511.03939","title":"RLHF: A comprehensive Survey for Cultural, Multimodal and Low Latency Alignment Methods","created":"2025-11-06","cited_by_count":2,"area":"alignment"},{"id":"2511.11551","title":"Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping","created":"2025-11-14","cited_by_count":2,"area":"alignment"},{"id":"2604.00310","title":"CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment","created":"2026-03-31","cited_by_count":2,"area":"alignment"},{"id":"2606.11201","title":"To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending","created":"2026-04-22","cited_by_count":2,"area":"alignment"},{"id":"2606.21102","title":"Incoherent Values? Probing LLM Preferences Through Parametric Variation","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2510.06391","title":"Reward Model Perspectives: Whose Opinions Do Reward Models Reward?","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2602.03073","title":"TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT","created":"2026-02-03","cited_by_count":1,"area":"alignment"},{"id":"2605.01899","title":"Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment","created":"2026-05-03","cited_by_count":1,"area":"alignment"},{"id":"2605.05003","title":"Misaligned by Reward: Socially Undesirable Preferences in LLMs","created":"2026-05-06","cited_by_count":1,"area":"alignment"},{"id":"2510.05465","title":"VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models","created":"2025-10-06","cited_by_count":0,"area":"alignment"},{"id":"2511.17256","title":"Cross-cultural value alignment frameworks for responsible AI governance: Evidence from China-West comparative analysis","created":"2025-11-21","cited_by_count":0,"area":"alignment"},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2601.06157","title":"ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment","created":"2026-01-06","cited_by_count":0,"area":"alignment"},{"id":"2602.08377","title":"Reinforcement Learning with Backtracking Feedback","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"id":"2602.15338","title":"Discovering Implicit Large Language Model Alignment Objectives","created":"2026-02-17","cited_by_count":0,"area":"alignment"},{"id":"2605.11712","title":"Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2606.06037","title":"SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech","created":"2026-06-04","cited_by_count":0,"area":"alignment"},{"id":"2607.00572","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2608.07642","title":"Contextual Value Alignment via Multilayer Combinatorial Fusion","created":"2026-08-07","cited_by_count":0,"area":"alignment"},{"id":"2608.12368","title":"Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments","created":"2026-07-14","cited_by_count":0,"area":"alignment"},{"id":"2608.12373","title":"Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese","created":"2026-07-21","cited_by_count":0,"area":"alignment"},{"id":"2608.18096","title":"MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2609.04022","title":"Representational alignment yields generalizable safety in language models","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.21094","title":"Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models","created":"2026-09-17","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"}],"next_cursor":null}