{"total":207,"rows":[{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437,"area":null},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367,"area":"agents"},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212,"area":"agents"},{"id":"2311.04892","title":"Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs","created":"2023-11-08","cited_by_count":199,"area":"lr"},{"id":"2311.09618","title":"Simulating Opinion Dynamics with Networks of LLM-based Agents","created":"2023-11-16","cited_by_count":154,"area":"agents"},{"id":"2310.11501","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","created":"2023-10-17","cited_by_count":97,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82,"area":"agents"},{"id":"2309.07034","title":"Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting","created":"2023-09-13","cited_by_count":81,"area":null},{"id":"2502.16761","title":"Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions","created":"2025-02-24","cited_by_count":66,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2309.12309","title":"Rehearsal: Simulating Conflict to Teach Conflict Resolution","created":"2023-09-21","cited_by_count":55,"area":null},{"id":"2402.05779","title":"Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images","created":"2024-02-08","cited_by_count":55,"area":"mllm"},{"id":"2404.10199","title":"CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting","created":"2024-04-16","cited_by_count":55,"area":null},{"id":"2308.03656","title":"Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench","created":"2023-08-07","cited_by_count":54,"area":null},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54,"area":"alignment"},{"id":"2402.04105","title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","created":"2024-02-06","cited_by_count":51,"area":null},{"id":"2402.18144","title":"Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information","created":"2024-02-28","cited_by_count":49,"area":null},{"id":"2408.15204","title":"Can Unconfident LLM Annotations Be Used for Confident Conclusions?","created":"2024-08-27","cited_by_count":49,"area":null},{"id":"2311.09718","title":"You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments","created":"2023-11-16","cited_by_count":48,"area":null},{"id":"2310.18168","title":"Personas as a Way to Model Truthfulness in Language Models","created":"2023-10-27","cited_by_count":47,"area":null},{"id":"2311.06025","title":"ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences","created":"2023-11-10","cited_by_count":43,"area":"alignment"},{"id":"2306.11932","title":"Opportunities and Risks of LLMs for Scalable Deliberation with Polis","created":"2023-06-20","cited_by_count":42,"area":null},{"id":"2507.16076","title":"The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models","created":"2025-07-21","cited_by_count":42,"area":null},{"id":"2403.03121","title":"Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution","created":"2024-03-05","cited_by_count":40,"area":null},{"id":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40,"area":"safety"},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35,"area":null},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2406.00888","title":"Aligning Language Models with Demonstrated Feedback","created":"2024-06-02","cited_by_count":34,"area":"alignment"},{"id":"2504.07114","title":"ChatBench: From Static Benchmarks to Human-AI Evaluation","created":"2025-03-22","cited_by_count":34,"area":null},{"id":"2408.16629","title":"LLMs generate structurally realistic social networks but overestimate political homophily","created":"2024-08-29","cited_by_count":33,"area":null},{"id":"2401.08495","title":"Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans","created":"2024-01-16","cited_by_count":31,"area":null},{"id":"2501.17420","title":"Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models","created":"2025-01-29","cited_by_count":30,"area":"agents"},{"id":"2307.09162","title":"Unveiling Gender Bias in Terms of Profession Across LLMs: Analyzing and Addressing Sociological Implications","created":"2023-07-18","cited_by_count":29,"area":null},{"id":"2405.02501","title":"PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning","created":"2024-05-03","cited_by_count":29,"area":null},{"id":"2503.15484","title":"Value Profiles for Encoding Human Variation","created":"2025-03-19","cited_by_count":29,"area":"alignment"},{"id":"2410.14012","title":"LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education","created":"2024-10-17","cited_by_count":28,"area":null},{"id":"2402.02056","title":"AnthroScore: A Computational Linguistic Measure of Anthropomorphism","created":"2024-02-03","cited_by_count":27,"area":null},{"id":"2406.11107","title":"Exploring Safety-Utility Trade-Offs in Personalized Language Models","created":"2024-06-17","cited_by_count":27,"area":null},{"id":"2411.12405","title":"Evaluating the Prompt Steerability of Large Language Models","created":"2024-11-19","cited_by_count":27,"area":null},{"id":"2501.02295","title":"Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection","created":"2025-01-04","cited_by_count":27,"area":"lr"},{"id":"2409.16605","title":"Evaluating and Enhancing Large Language Models for Novelty Assessment in Scholarly Publications","created":"2024-09-25","cited_by_count":26,"area":null},{"id":"2406.10486","title":"Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?","created":"2024-06-15","cited_by_count":25,"area":null},{"id":"2505.15229","title":"Multilingual Prompting for Improving LLM Generation Diversity","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2505.16467","title":"Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization","created":"2025-05-22","cited_by_count":24,"area":null},{"id":"2406.14462","title":"Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas","created":"2024-06-20","cited_by_count":23,"area":null},{"id":"2406.11661","title":"Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"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,"area":"alignment"},{"id":"2407.02099","title":"Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior","created":"2024-07-02","cited_by_count":21,"area":null},{"id":"2307.03360","title":"Evaluating Biased Attitude Associations of Language Models in an Intersectional Context","created":"2023-07-07","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":"2408.16482","title":"Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning","created":"2024-08-29","cited_by_count":19,"area":"alignment"},{"id":"2506.00582","title":"Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs","created":"2025-05-31","cited_by_count":19,"area":null},{"id":"2503.08588","title":"BiasEdit: Debiasing Stereotyped Language Models via Model Editing","created":"2025-03-11","cited_by_count":18,"area":null},{"id":"2510.11408","title":"Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification","created":"2025-10-13","cited_by_count":18,"area":null},{"id":"2402.01705","title":"Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation","created":"2024-01-25","cited_by_count":17,"area":null},{"id":"2404.03192","title":"Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2406.15625","title":"Shortcomings of LLMs for Low-Resource Translation: Retrieval and Understanding are Both the Problem","created":"2024-06-21","cited_by_count":17,"area":null},{"id":"2503.06987","title":"Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluations","created":"2025-03-10","cited_by_count":16,"area":null},{"id":"2404.04204","title":"Social Skill Training with Large Language Models","created":"2024-04-05","cited_by_count":15,"area":null},{"id":"2408.06518","title":"Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models","created":"2024-08-12","cited_by_count":15,"area":null},{"id":"2502.19312","title":"FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users","created":"2025-02-26","cited_by_count":15,"area":"alignment"},{"id":"2601.07110","title":"The Need for a Socially-Grounded Persona Framework for User Simulation","created":"2026-01-12","cited_by_count":15,"area":null},{"id":"2406.04064","title":"Ask LLMs Directly, \"What shapes your bias?\": Measuring Social Bias in Large Language Models","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2407.12878","title":"Do LLMs have Consistent Values?","created":"2024-07-16","cited_by_count":14,"area":null},{"id":"2503.05371","title":"Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs","created":"2025-03-07","cited_by_count":14,"area":"mechinterp"},{"id":"2505.21693","title":"MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs","created":"2025-05-27","cited_by_count":13,"area":null},{"id":"2402.12255","title":"Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition","created":"2024-02-19","cited_by_count":12,"area":null},{"id":"2407.06908","title":"Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2410.15299","title":"Does ChatGPT Have a Poetic Style?","created":"2024-10-20","cited_by_count":12,"area":null},{"id":"2502.13259","title":"HumT DumT: Measuring and controlling human-like language in LLMs","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2406.13993","title":"Exploring Changes in Nation Perception with Nationality-Assigned Personas in LLMs","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2407.16891","title":"Cultural Value Differences of LLMs: Prompt, Language, and Model Size","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2410.08820","title":"Which Demographics do LLMs Default to During Annotation?","created":"2024-10-11","cited_by_count":10,"area":null},{"id":"2501.18045","title":"From tools to thieves: Measuring and understanding public perceptions of AI through crowdsourced metaphors","created":"2025-01-29","cited_by_count":10,"area":null},{"id":"2505.09056","title":"A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias","created":"2025-05-14","cited_by_count":10,"area":null},{"id":"2508.15830","title":"DAIQ: Auditing Demographic Attribute Inference from Question in LLMs","created":"2025-08-18","cited_by_count":10,"area":null},{"id":"2510.10328","title":"Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model's Empathy","created":"2025-10-11","cited_by_count":10,"area":null},{"id":"2504.04934","title":"Boosting Relational Deep Learning with Pretrained Tabular Models","created":"2025-04-07","cited_by_count":9,"area":null},{"id":"2504.17993","title":"Improving Language Model Personas via Rationalization with Psychological Scaffolds","created":"2025-04-25","cited_by_count":9,"area":null},{"id":"2509.21972","title":"From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Education","created":"2025-09-26","cited_by_count":9,"area":null},{"id":"2601.18572","title":"One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization","created":"2026-01-26","cited_by_count":9,"area":null},{"id":"2503.02776","title":"Implicit Bias in LLMs: A Survey","created":"2025-03-04","cited_by_count":8,"area":"safety"},{"id":"2506.19352","title":"Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation","created":"2025-06-24","cited_by_count":8,"area":null},{"id":"2509.04373","title":"Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases","created":"2025-09-04","cited_by_count":8,"area":null},{"id":"2411.03888","title":"Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models","created":"2024-11-06","cited_by_count":7,"area":"mllm"},{"id":"2502.19721","title":"Unsupervised Concept Vector Extraction for Bias Control in LLMs","created":"2025-02-27","cited_by_count":7,"area":"mechinterp"},{"id":"2312.06147","title":"\"What's important here?\": Opportunities and Challenges of Using LLMs in Retrieving Information from Web Interfaces","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2409.13588","title":"ChainBuddy: An AI Agent System for Generating LLM Pipelines","created":"2024-09-20","cited_by_count":6,"area":"agents"},{"id":"2503.00333","title":"More of the Same: Persistent Representational Harms Under Increased Representation","created":"2025-03-01","cited_by_count":6,"area":null},{"id":"2503.01030","title":"Language Models Predict Empathy Gaps Between Social In-groups and Out-groups","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2505.00003","title":"A Review of Incorporating Psychological Theories in LLMs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2508.15831","title":"Who's Asking? Investigating Bias Through the Lens of Disability Framed Queries in LLMs","created":"2025-08-18","cited_by_count":6,"area":null},{"id":"2510.11997","title":"SAGE: A Top-Down Bottom-Up Knowledge-Grounded User Simulator for Multi-turn AGent Evaluation","created":"2025-10-13","cited_by_count":6,"area":null},{"id":"2403.11456","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2404.07475","title":"Laissez-Faire Harms: Algorithmic Biases in Generative Language Models","created":"2024-04-11","cited_by_count":5,"area":null},{"id":"2405.03098","title":"FairMonitor: A Dual-framework for Detecting Stereotypes and Biases in Large Language Models","created":"2024-05-06","cited_by_count":5,"area":null},{"id":"2406.17385","title":"Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance","created":"2024-06-25","cited_by_count":5,"area":null}],"next_cursor":"100"}