{"list":"other","total":181,"rows":[{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192},{"id":"2311.05553","title":"Removing RLHF Protections in GPT-4 via Fine-Tuning","created":"2023-11-09","cited_by_count":171},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148},{"id":"2012.15738","title":"Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences","created":"2020-12-31","cited_by_count":135},{"id":"2402.10571","title":"Direct Preference Optimization with an Offset","created":"2024-02-16","cited_by_count":122},{"id":"2309.12342","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","created":"2023-08-25","cited_by_count":112},{"id":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","cited_by_count":111},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107},{"id":"2312.00738","title":"SeaLLMs -- Large Language Models for Southeast Asia","created":"2023-12-01","cited_by_count":104},{"id":"2402.04049","title":"Systematic Biases in LLM Simulations of Debates","created":"2024-02-06","cited_by_count":99},{"id":"2401.13136","title":"The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts","created":"2024-01-23","cited_by_count":94},{"id":"2310.15337","title":"Moral Foundations of Large Language Models","created":"2023-10-23","cited_by_count":85},{"id":"2405.18166","title":"Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing","created":"2024-05-28","cited_by_count":79},{"id":"2405.20253","title":"Evaluating Large Language Model Biases in Persona-Steered Generation","created":"2024-05-30","cited_by_count":78},{"id":"2403.07865","title":"CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion","created":"2024-03-12","cited_by_count":76},{"id":"2309.12053","title":"AceGPT, Localizing Large Language Models in Arabic","created":"2023-09-21","cited_by_count":75},{"id":"2401.06561","title":"Intention Analysis Makes LLMs A Good Jailbreak Defender","created":"2024-01-12","cited_by_count":74},{"id":"2407.17387","title":"PERSONA: A Reproducible Testbed for Pluralistic Alignment","created":"2024-07-24","cited_by_count":73},{"id":"2312.15997","title":"Aligning Large Language Models with Human Preferences through Representation Engineering","created":"2023-12-26","cited_by_count":71},{"id":"2410.24190","title":"Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters","created":"2024-10-31","cited_by_count":71},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66},{"id":"2310.07251","title":"Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs","created":"2023-10-11","cited_by_count":64},{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63},{"id":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61},{"id":"2411.04427","title":"One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity","created":"2024-11-07","cited_by_count":58},{"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},{"id":"2402.17649","title":"Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs","created":"2024-02-27","cited_by_count":55},{"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},{"id":"2406.11827","title":"WPO: Enhancing RLHF with Weighted Preference Optimization","created":"2024-06-17","cited_by_count":54},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50},{"id":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50},{"id":"2404.18460","title":"Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in","created":"2024-04-29","cited_by_count":46},{"id":"2403.08424","title":"Distract Large Language Models for Automatic Jailbreak Attack","created":"2024-03-13","cited_by_count":45},{"id":"2401.15449","title":"Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation","created":"2024-01-27","cited_by_count":44},{"id":"2404.17287","title":"When to Trust LLMs: Aligning Confidence with Response Quality","created":"2024-04-26","cited_by_count":43},{"id":"2407.02552","title":"RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs","created":"2024-07-02","cited_by_count":43},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42},{"id":"2502.18968","title":"Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles","created":"2025-02-26","cited_by_count":41},{"id":"2312.00027","title":"Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections","created":"2023-11-15","cited_by_count":39},{"id":"2311.06899","title":"Flames: Benchmarking Value Alignment of LLMs in Chinese","created":"2023-11-12","cited_by_count":37},{"id":"2101.06060","title":"The Challenge of Value Alignment: from Fairer Algorithms to AI Safety","created":"2021-01-15","cited_by_count":35},{"id":"2401.16656","title":"Gradient-Based Language Model Red Teaming","created":"2024-01-30","cited_by_count":34},{"id":"2410.03868","title":"Can Language Models Reason about Individualistic Human Values and Preferences?","created":"2024-10-04","cited_by_count":34},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32},{"id":"2403.14952","title":"Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation","created":"2024-03-22","cited_by_count":32},{"id":"2406.11801","title":"Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations","created":"2024-06-17","cited_by_count":32},{"id":"2505.17147","title":"MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming","created":"2025-05-22","cited_by_count":32},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","cited_by_count":31},{"id":"2409.05283","title":"On the Relationship between Truth and Political Bias in Language Models","created":"2024-09-09","cited_by_count":31},{"id":"2408.08808","title":"Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge","created":"2024-08-16","cited_by_count":30},{"id":"2310.03304","title":"Learning Personalized Alignment for Evaluating Open-ended Text Generation","created":"2023-10-05","cited_by_count":29},{"id":"2311.08685","title":"Safer-Instruct: Aligning Language Models with Automated Preference Data","created":"2023-11-15","cited_by_count":27},{"id":"2503.17662","title":"Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning","created":"2025-03-22","cited_by_count":27},{"id":"2312.07401","title":"On Diversified Preferences of Large Language Model Alignment","created":"2023-12-12","cited_by_count":26},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26},{"id":"2503.09347","title":"Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts","created":"2025-03-12","cited_by_count":26},{"id":"2409.16783","title":"Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction","created":"2024-09-25","cited_by_count":25},{"id":"2402.04477","title":"Detecting Mode Collapse in Language Models via Narration","created":"2024-02-06","cited_by_count":24},{"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},{"id":"2306.16244","title":"CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2023-06-28","cited_by_count":23},{"id":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21},{"id":"2402.11114","title":"Whose Emotions and Moral Sentiments Do Language Models Reflect?","created":"2024-02-16","cited_by_count":20},{"id":"2502.12858","title":"Rejected Dialects: Biases Against African American Language in Reward Models","created":"2025-02-18","cited_by_count":20},{"id":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","cited_by_count":19},{"id":"2311.08385","title":"Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning","created":"2023-11-14","cited_by_count":19},{"id":"2410.06554","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","created":"2024-10-09","cited_by_count":19},{"id":"2410.14309","title":"LoGU: Long-form Generation with Uncertainty Expressions","created":"2024-10-18","cited_by_count":19},{"id":"2410.16027","title":"ComPO: Community Preferences for Language Model Personalization","created":"2024-10-21","cited_by_count":19},{"id":"2501.11549","title":"Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas","created":"2025-01-20","cited_by_count":19},{"id":"2401.10352","title":"Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys","created":"2024-01-18","cited_by_count":18},{"id":"2402.17358","title":"SoFA: Shielded On-the-fly Alignment via Priority Rule Following","created":"2024-02-27","cited_by_count":18},{"id":"2503.00231","title":"Jawaher: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking","created":"2025-02-28","cited_by_count":18},{"id":"2505.01015","title":"Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items","created":"2025-05-02","cited_by_count":18},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18},{"id":"2212.10720","title":"MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions","created":"2022-12-21","cited_by_count":17},{"id":"2403.13213","title":"From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards","created":"2024-03-20","cited_by_count":17},{"id":"2502.13775","title":"VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare","created":"2025-02-19","cited_by_count":17},{"id":"2503.00771","title":"Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity","created":"2025-03-02","cited_by_count":17},{"id":"2204.09438","title":"A Corpus for Understanding and Generating Moral Stories","created":"2022-04-20","cited_by_count":16},{"id":"2305.14702","title":"DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4","created":"2023-05-24","cited_by_count":16},{"id":"2503.14603","title":"Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM","created":"2025-03-18","cited_by_count":16},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16},{"id":"2507.11316","title":"Internal Value Alignment in Large Language Models through Controlled Value Vector Activation","created":"2025-07-15","cited_by_count":16},{"id":"2312.14591","title":"Reasons to Reject? Aligning Language Models with Judgments","created":"2023-12-22","cited_by_count":15},{"id":"2406.03030","title":"From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation","created":"2024-06-05","cited_by_count":15},{"id":"2410.18359","title":"Improving Model Factuality with Fine-grained Critique-based Evaluator","created":"2024-10-24","cited_by_count":15},{"id":"2505.19484","title":"CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis","created":"2025-05-26","cited_by_count":15},{"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},{"id":"2103.07011","title":"Towards Socially Intelligent Agents with Mental State Transition and Human Utility","created":"2021-03-12","cited_by_count":14},{"id":"2406.06435","title":"Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain","created":"2024-06-10","cited_by_count":14},{"id":"2406.13230","title":"Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding","created":"2024-06-19","cited_by_count":14},{"id":"2502.10762","title":"Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation","created":"2025-02-15","cited_by_count":14},{"id":"2210.07652","title":"Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values","created":"2022-10-14","cited_by_count":13},{"id":"2304.00416","title":"Towards Healthy AI: Large Language Models Need Therapists Too","created":"2023-04-02","cited_by_count":13}],"next_cursor":"100"}