{"total":189,"rows":[{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443,"area":"safety"},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773,"area":null},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"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":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215,"area":null},{"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":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2310.17976","title":"InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews","created":"2023-10-27","cited_by_count":179,"area":null},{"id":"2302.03494","title":"A Categorical Archive of ChatGPT Failures","created":"2023-02-06","cited_by_count":168,"area":null},{"id":"2402.16786","title":"Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models","created":"2024-02-26","cited_by_count":162,"area":null},{"id":"2304.01852","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","created":"2023-04-04","cited_by_count":154,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2309.07930","title":"Generative AI","created":"2023-09-13","cited_by_count":120,"area":null},{"id":"2402.01789","title":"The Political Preferences of LLMs","created":"2024-02-02","cited_by_count":84,"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":"2306.07951","title":"Questioning the Survey Responses of Large Language Models","created":"2023-06-13","cited_by_count":74,"area":null},{"id":"2406.16937","title":"A Complete Survey on LLM-based AI Chatbots","created":"2024-06-17","cited_by_count":71,"area":null},{"id":"2410.24190","title":"Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters","created":"2024-10-31","cited_by_count":71,"area":null},{"id":"2304.07333","title":"The Self-Perception and Political Biases of ChatGPT","created":"2023-04-14","cited_by_count":66,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2304.06488","title":"One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era","created":"2023-04-04","cited_by_count":55,"area":null},{"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":"2402.17649","title":"Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs","created":"2024-02-27","cited_by_count":55,"area":null},{"id":"2407.06576","title":"Virtual Personas for Language Models via an Anthology of Backstories","created":"2024-07-09","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":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2302.07267","title":"Diminished Diversity-of-Thought in a Standard Large Language Model","created":"2023-02-13","cited_by_count":45,"area":"lr"},{"id":"2309.01291","title":"Generative Social Choice","created":"2023-09-03","cited_by_count":43,"area":null},{"id":"2310.12481","title":"Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models","created":"2023-10-19","cited_by_count":43,"area":null},{"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":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2502.16534","title":"Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs","created":"2025-02-23","cited_by_count":39,"area":null},{"id":"2304.08979","title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","created":"2023-04-18","cited_by_count":37,"area":null},{"id":"2408.06929","title":"Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas","created":"2024-08-13","cited_by_count":37,"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":"2408.16629","title":"LLMs generate structurally realistic social networks but overestimate political homophily","created":"2024-08-29","cited_by_count":33,"area":null},{"id":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29,"area":"lr"},{"id":"2409.01754","title":"Empirical evidence of Large Language Model's influence on human spoken communication","created":"2024-09-03","cited_by_count":27,"area":null},{"id":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2402.11725","title":"How Susceptible are Large Language Models to Ideological Manipulation?","created":"2024-02-18","cited_by_count":26,"area":null},{"id":"2501.05171","title":"Emergence of polarization in networks of large language model agents","created":"2025-01-09","cited_by_count":26,"area":"agents"},{"id":"2502.08395","title":"IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance","created":"2025-02-12","cited_by_count":26,"area":null},{"id":"2304.00228","title":"Accuracy and Political Bias of News Source Credibility Ratings by Large Language Models","created":"2023-04-01","cited_by_count":25,"area":null},{"id":"2501.18081","title":"Normative Evaluation of Large Language Models with Everyday Moral Dilemmas","created":"2025-01-30","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":"2402.11114","title":"Whose Emotions and Moral Sentiments Do Language Models Reflect?","created":"2024-02-16","cited_by_count":20,"area":null},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","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":"2506.12657","title":"Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics","created":"2025-06-14","cited_by_count":19,"area":null},{"id":"2406.11854","title":"Attributions toward Artificial Agents in a modified Moral Turing Test","created":"2024-04-03","cited_by_count":18,"area":null},{"id":"2409.12126","title":"Linguini: A benchmark for language-agnostic linguistic reasoning","created":"2024-09-18","cited_by_count":17,"area":"lr"},{"id":"2502.13775","title":"VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare","created":"2025-02-19","cited_by_count":17,"area":"alignment"},{"id":"2306.03102","title":"ChatGPT is a Remarkable Tool -- For Experts","created":"2023-06-02","cited_by_count":16,"area":null},{"id":"2306.04308","title":"Personality testing of Large Language Models: Limited temporal stability, but highlighted prosociality","created":"2023-06-07","cited_by_count":16,"area":null},{"id":"2312.09545","title":"Does GPT-4 surpass human performance in linguistic pragmatics?","created":"2023-12-15","cited_by_count":16,"area":null},{"id":"2405.13974","title":"CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models","created":"2024-05-22","cited_by_count":16,"area":null},{"id":"2409.08330","title":"Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue","created":"2024-09-12","cited_by_count":16,"area":null},{"id":"2412.14843","title":"Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas","created":"2024-12-19","cited_by_count":16,"area":null},{"id":"2502.09369","title":"Language Agents as Digital Representatives in Collective Decision-Making","created":"2025-02-13","cited_by_count":16,"area":"agents"},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"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":"2405.05506","title":"Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias","created":"2024-05-09","cited_by_count":15,"area":null},{"id":"2503.16148","title":"Only a Little to the Left: A Theory-grounded Measure of Political Bias in Large Language Models","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2403.13592","title":"Llama meets EU: Investigating the European Political Spectrum through the Lens of LLMs","created":"2024-03-20","cited_by_count":14,"area":null},{"id":"2407.18008","title":"GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy","created":"2024-07-25","cited_by_count":14,"area":null},{"id":"2410.19238","title":"Designing AI-Agents with Personalities: A Psychometric Approach","created":"2024-10-25","cited_by_count":14,"area":"agents"},{"id":"2407.08563","title":"Vox Populi, Vox AI? Using Language Models to Estimate German Public Opinion","created":"2024-07-11","cited_by_count":13,"area":null},{"id":"2506.20020","title":"Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning","created":"2025-06-24","cited_by_count":13,"area":"lr"},{"id":"2406.19317","title":"Jump Starting Bandits with LLM-Generated Prior Knowledge","created":"2024-06-27","cited_by_count":12,"area":null},{"id":"2505.22354","title":"LLMs Struggle to Reject False Presuppositions when Misinformation Stakes are High","created":"2025-05-28","cited_by_count":12,"area":null},{"id":"2312.05235","title":"Generative AI in Higher Education: Seeing ChatGPT Through Universities' Policies, Resources, and Guidelines","created":"2023-12-08","cited_by_count":11,"area":null},{"id":"2403.17125","title":"The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition","created":"2024-03-25","cited_by_count":10,"area":null},{"id":"2407.11409","title":"Representation Bias in Political Sample Simulations with Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2506.08952","title":"Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2309.10448","title":"Human-AI Interactions and Societal Pitfalls","created":"2023-09-19","cited_by_count":9,"area":null},{"id":"2310.16269","title":"Multilingual Coarse Political Stance Classification of Media. The Editorial Line of a ChatGPT and Bard Newspaper","created":"2023-10-25","cited_by_count":9,"area":null},{"id":"2409.03843","title":"Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption","created":"2024-09-05","cited_by_count":9,"area":null},{"id":"2503.10649","title":"Measuring Political Preferences in AI Systems: An Integrative Approach","created":"2025-03-04","cited_by_count":9,"area":null},{"id":"2302.07371","title":"BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models","created":"2023-02-14","cited_by_count":8,"area":null},{"id":"2402.09346","title":"LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2405.19323","title":"Are Large Language Models Chameleons? An Attempt to Simulate Social Surveys","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2410.13517","title":"Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2504.19674","title":"SAGE: A Generic Framework for LLM Safety Evaluation","created":"2025-04-28","cited_by_count":8,"area":"safety"},{"id":"2510.11586","title":"Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2601.08785","title":"Uncovering Political Bias in Large Language Models using Parliamentary Voting Records","created":"2026-01-13","cited_by_count":8,"area":null},{"id":"2407.08495","title":"Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024","created":"2024-07-11","cited_by_count":7,"area":"rag"},{"id":"2503.23688","title":"Mapping Geopolitical Bias in 11 Large Language Models: A Bilingual, Dual-Framing Analysis of U.S.-China Tensions","created":"2025-03-31","cited_by_count":7,"area":null},{"id":"2504.12911","title":"Benchmarking Multi-National Value Alignment for Large Language Models","created":"2025-04-17","cited_by_count":7,"area":"alignment"},{"id":"2505.19776","title":"Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2509.22367","title":"What Is The Political Content in LLMs' Pre- and Post-Training Data?","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2306.03423","title":"I'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language Models","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2406.14023","title":"Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2406.14155","title":"Aligning Large Language Models with Diverse Political Viewpoints","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2406.19238","title":"Revealing Fine-Grained Values and Opinions in Large Language Models","created":"2024-06-27","cited_by_count":5,"area":null},{"id":"2409.09045","title":"United in Diversity? Contextual Biases in LLM-Based Predictions of the 2024 European Parliament Elections","created":"2024-08-29","cited_by_count":5,"area":null},{"id":"2501.16355","title":"How Strategic Agents Respond: Comparing Analytical Models with LLM-Generated Responses in Strategic Classification","created":"2025-01-20","cited_by_count":5,"area":"agents"}],"next_cursor":"100"}