{"total":97,"rows":[{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167,"area":null},{"id":"2406.07814","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","created":"2024-06-12","cited_by_count":123,"area":"alignment"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2410.02683","title":"DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life","created":"2024-10-03","cited_by_count":59,"area":null},{"id":"2504.15236","title":"Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions","created":"2025-04-21","cited_by_count":52,"area":null},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50,"area":null},{"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,"area":null},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2402.10426","title":"DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection","created":"2024-02-16","cited_by_count":41,"area":null},{"id":"2502.12057","title":"Culture is Not Trivia: Sociocultural Theory for Cultural NLP","created":"2025-02-17","cited_by_count":40,"area":null},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2406.19643","title":"Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation","created":"2024-06-28","cited_by_count":29,"area":"agents"},{"id":"2411.12405","title":"Evaluating the Prompt Steerability of Large Language Models","created":"2024-11-19","cited_by_count":27,"area":null},{"id":"2309.13356","title":"Probing the Moral Development of Large Language Models through Defining Issues Test","created":"2023-09-23","cited_by_count":25,"area":"lr"},{"id":"2407.10725","title":"CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses","created":"2024-07-15","cited_by_count":23,"area":null},{"id":"2406.17675","title":"Evaluating Large Language Models with Psychometrics","created":"2024-06-25","cited_by_count":22,"area":null},{"id":"2506.01080","title":"The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process","created":"2025-06-01","cited_by_count":21,"area":"alignment"},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2310.15431","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2409.12106","title":"Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2406.11622","title":"Building Knowledge-Guided Lexica to Model Cultural Variation","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2411.03665","title":"Evaluating Moral Beliefs across LLMs through a Pluralistic Framework","created":"2024-11-06","cited_by_count":11,"area":null},{"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":"2507.13383","title":"Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models","created":"2025-07-15","cited_by_count":11,"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":"2410.16665","title":"SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior","created":"2024-10-22","cited_by_count":10,"area":null},{"id":"2504.10823","title":"CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2505.23785","title":"Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale","created":"2025-05-23","cited_by_count":10,"area":null},{"id":"2507.13579","title":"Learning to summarize user information for personalized reinforcement learning from human feedback","created":"2025-07-17","cited_by_count":10,"area":"alignment"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2603.06495","title":"COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics","created":"2026-03-06","cited_by_count":8,"area":"mechinterp"},{"id":"2510.14591","title":"Just-In-Time Objectives: A General Approach for Specialized AI Interactions","created":"2025-10-16","cited_by_count":7,"area":null},{"id":"2512.01351","title":"Benchmarking Overton Pluralism in LLMs","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2410.23630","title":"Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2501.03266","title":"LLM Content Moderation and User Satisfaction: Evidence from Response Refusals in Chatbot Arena","created":"2025-01-04","cited_by_count":6,"area":"safety"},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","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":"2410.04054","title":"Large Language Models can Achieve Social Balance","created":"2024-10-05","cited_by_count":5,"area":null},{"id":"2506.22957","title":"Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models","created":"2025-06-28","cited_by_count":5,"area":"agents"},{"id":"2510.18526","title":"Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2601.08951","title":"PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2311.02049","title":"Post Turing: Mapping the landscape of LLM Evaluation","created":"2023-11-03","cited_by_count":4,"area":null},{"id":"2407.03232","title":"Single Character Perturbations Break LLM Alignment","created":"2024-07-03","cited_by_count":4,"area":"alignment"},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2502.02444","title":"Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models","created":"2025-02-04","cited_by_count":4,"area":null},{"id":"2505.11861","title":"Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity","created":"2025-05-17","cited_by_count":4,"area":"alignment"},{"id":"2505.13531","title":"AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2509.14434","title":"Value Alignment of Social Media Ranking Algorithms","created":"2025-09-17","cited_by_count":4,"area":"alignment"},{"id":"2509.25897","title":"RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","cited_by_count":4,"area":"alignment"},{"id":"2312.17479","title":"Culturally-Attuned Moral Machines: Implicit Learning of Human Value Systems by AI through Inverse Reinforcement Learning","created":"2023-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2411.17338","title":"Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2504.19255","title":"The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approach","created":"2025-04-27","cited_by_count":3,"area":"lr"},{"id":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2311.02294","title":"LLMs grasp morality in concept","created":"2023-11-04","cited_by_count":2,"area":null},{"id":"2410.17271","title":"Rules, Cases, and Reasoning: Positivist Legal Theory as a Framework for Pluralistic AI Alignment","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2507.09037","title":"ALIGN: Prompt-based Attribute Alignment for Reliable, Responsible, and Personalized LLM-based Decision-Making","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2509.11311","title":"Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble","created":"2025-09-14","cited_by_count":2,"area":"alignment"},{"id":"2601.03483","title":"CALM: Culturally Self-Aware Language Models","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2604.10673","title":"Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment","created":"2026-04-12","cited_by_count":2,"area":"alignment"},{"id":"2605.18738","title":"What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2311.17017","title":"Foundational Moral Values for AI Alignment","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2402.15473","title":"Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF: A Case-Study in E-Commerce Opinion Summarization","created":"2024-02-23","cited_by_count":1,"area":"alignment"},{"id":"2410.05496","title":"Intuitions of Compromise: Utilitarianism vs. Contractualism","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2502.19463","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","created":"2025-02-26","cited_by_count":1,"area":"alignment"},{"id":"2510.06093","title":"Classical AI vs. LLMs for Decision-Maker Alignment in Health Insurance Choices","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2601.09896","title":"The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2602.20759","title":"Overton Pluralistic Reinforcement Learning for Large Language Models","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.15527","title":"Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph","created":"2026-03-16","cited_by_count":1,"area":"alignment"},{"id":"2604.06210","title":"Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2604.12138","title":"Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions","created":"2026-04-13","cited_by_count":1,"area":"rag"},{"id":"2605.06987","title":"Response Time Enhances Alignment with Heterogeneous Preferences","created":"2026-05-07","cited_by_count":1,"area":"alignment"},{"id":"2606.18774","title":"RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2609.05800","title":"Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment","created":"2026-09-05","cited_by_count":1,"area":"alignment"},{"id":"2411.15051","title":"Fantastic Biases (What are They) and Where to Find Them","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2506.00242","title":"Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.05171","title":"Towards provable probabilistic safety for scalable embodied AI systems","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2509.08022","title":"DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values","created":"2025-09-09","cited_by_count":0,"area":"alignment"},{"id":"2510.01976","title":"Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2601.04207","title":"Ideology as a Problem: Lightweight Logit Steering for Annotator-Specific Alignment in Social Media Analysis","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2603.02420","title":"Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2603.17838","title":"Event-Centric Human Value Understanding in News-Domain Texts: An Actor-Conditioned, Multi-Granularity Benchmark","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.20685","title":"MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment","created":"2026-04-22","cited_by_count":0,"area":"alignment"},{"id":"2604.20805","title":"Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.11865","title":"Variance-aware Reward Modeling with Anchor Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2606.03312","title":"RobotValues: Evaluating Household Robots When Human Values Conflict","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.27578","title":"PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration","created":"2026-06-25","cited_by_count":0,"area":"alignment"},{"id":"2607.20270","title":"Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.20405","title":"ARGUS: Theory-of-Mind Guided Argument Generation with Strategy-Aware Planning and Knowledge Grounding","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.38260","title":"ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39701","title":"Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}