{"total":191,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129,"area":null},{"id":"2306.00622","title":"ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing","created":"2023-06-01","cited_by_count":122,"area":null},{"id":"2306.07899","title":"Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks","created":"2023-06-13","cited_by_count":103,"area":null},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97,"area":null},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91,"area":null},{"id":"2404.12259","title":"Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM","created":"2024-04-18","cited_by_count":78,"area":null},{"id":"2306.00176","title":"Automated Annotation with Generative AI Requires Validation","created":"2023-05-31","cited_by_count":76,"area":null},{"id":"2306.07951","title":"Questioning the Survey Responses of Large Language Models","created":"2023-06-13","cited_by_count":74,"area":null},{"id":"2404.04326","title":"Hypothesis Generation with Large Language Models","created":"2024-04-05","cited_by_count":71,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"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":"2310.00737","title":"GenAI Against Humanity: Nefarious Applications of Generative Artificial Intelligence and Large Language Models","created":"2023-10-01","cited_by_count":42,"area":null},{"id":"2309.15847","title":"Disinformation Detection: An Evolving Challenge in the Age of LLMs","created":"2023-09-25","cited_by_count":41,"area":null},{"id":"2406.05972","title":"Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context","created":"2024-06-10","cited_by_count":41,"area":null},{"id":"2311.14693","title":"Benefits and Harms of Large Language Models in Digital Mental Health","created":"2023-11-07","cited_by_count":40,"area":null},{"id":"2306.04746","title":"Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models","created":"2023-06-07","cited_by_count":39,"area":null},{"id":"2305.14976","title":"GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP","created":"2023-05-24","cited_by_count":37,"area":null},{"id":"2308.10032","title":"GameEval: Evaluating LLMs on Conversational Games","created":"2023-08-19","cited_by_count":37,"area":null},{"id":"2307.02179","title":"Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning","created":"2023-07-05","cited_by_count":32,"area":null},{"id":"2306.13906","title":"Can GPT-4 Support Analysis of Textual Data in Tasks Requiring Highly Specialized Domain Expertise?","created":"2023-06-24","cited_by_count":31,"area":null},{"id":"2407.10747","title":"Codebook LLMs: Evaluating LLMs as Measurement Tools for Political Science Concepts","created":"2024-07-15","cited_by_count":30,"area":null},{"id":"2401.11839","title":"AI for social science and social science of AI: A Survey","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2409.19430","title":"'Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participants","created":"2024-09-28","cited_by_count":28,"area":null},{"id":"2402.11725","title":"How Susceptible are Large Language Models to Ideological Manipulation?","created":"2024-02-18","cited_by_count":26,"area":null},{"id":"2307.13912","title":"Embedding Democratic Values into Social Media AIs via Societal Objective Functions","created":"2023-07-26","cited_by_count":25,"area":null},{"id":"2504.12976","title":"Sparks of Science: Hypothesis Generation Using Structured Paper Data","created":"2025-04-17","cited_by_count":25,"area":null},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2305.14492","title":"Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment","created":"2023-05-23","cited_by_count":22,"area":null},{"id":"2309.17147","title":"Using Large Language Models for Qualitative Analysis can Introduce Serious Bias","created":"2023-09-29","cited_by_count":22,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2406.17675","title":"Evaluating Large Language Models with Psychometrics","created":"2024-06-25","cited_by_count":22,"area":null},{"id":"2405.19660","title":"PATIENT-{\\Psi}: Using Large Language Models to Simulate Patients for Training Mental Health Professionals","created":"2024-05-30","cited_by_count":21,"area":null},{"id":"2506.10150","title":"When Large Language Models are Reliable for Judging Empathic Communication","created":"2025-06-11","cited_by_count":21,"area":null},{"id":"2403.10750","title":"Depression Detection on Social Media with Large Language Models","created":"2024-03-16","cited_by_count":20,"area":null},{"id":"2410.20745","title":"Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models","created":"2024-10-28","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":"2305.14310","title":"Navigating Prompt Complexity for Zero-Shot Classification: A Study of Large Language Models in Computational Social Science","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2312.11518","title":"User Modeling in the Era of Large Language Models: Current Research and Future Directions","created":"2023-12-11","cited_by_count":18,"area":null},{"id":"2401.01519","title":"Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review","created":"2024-01-03","cited_by_count":17,"area":null},{"id":"2308.03051","title":"TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties","created":"2023-08-06","cited_by_count":16,"area":null},{"id":"2409.12538","title":"PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation","created":"2024-09-19","cited_by_count":16,"area":null},{"id":"2501.12557","title":"Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review","created":"2025-01-22","cited_by_count":16,"area":null},{"id":"2309.14379","title":"Machine-assisted quantitizing designs: augmenting humanities and social sciences with artificial intelligence","created":"2023-09-24","cited_by_count":15,"area":null},{"id":"2404.12691","title":"Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?","created":"2024-04-19","cited_by_count":15,"area":null},{"id":"2407.02039","title":"Prompt Stability Scoring for Text Annotation with Large Language Models","created":"2024-07-02","cited_by_count":15,"area":null},{"id":"2311.00687","title":"Improving Interpersonal Communication by Simulating Audiences with Language Models","created":"2023-11-01","cited_by_count":14,"area":null},{"id":"2402.01830","title":"PiCO: Peer Review in LLMs based on the Consistency Optimization","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2609.24052","title":"Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)","created":"2026-09-21","cited_by_count":14,"area":null},{"id":"2311.16639","title":"Positioning Political Texts with Large Language Models by Asking and Averaging","created":"2023-11-28","cited_by_count":13,"area":null},{"id":"2404.01602","title":"Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game","created":"2024-04-02","cited_by_count":13,"area":null},{"id":"2405.19740","title":"PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations","created":"2024-05-30","cited_by_count":13,"area":null},{"id":"2401.00284","title":"Evaluation is all you need. Prompting Generative Large Language Models for Annotation Tasks in the Social Sciences. A Primer using Open Models","created":"2023-12-30","cited_by_count":12,"area":null},{"id":"2401.04122","title":"From Prompt Engineering to Prompt Science With Human in the Loop","created":"2024-01-01","cited_by_count":12,"area":null},{"id":"2402.08755","title":"LLM-driven Imitation of Subrational Behavior : Illusion or Reality?","created":"2024-02-13","cited_by_count":12,"area":null},{"id":"2412.10415","title":"Generative Adversarial Reviews: When LLMs Become the Critic","created":"2024-12-09","cited_by_count":12,"area":null},{"id":"2506.19806","title":"LLM-Based Social Simulations Require a Boundary","created":"2025-06-24","cited_by_count":12,"area":null},{"id":"2306.02177","title":"Towards Coding Social Science Datasets with Language Models","created":"2023-06-03","cited_by_count":11,"area":null},{"id":"2312.09203","title":"Measurement in the Age of LLMs: An Application to Ideological Scaling","created":"2023-12-14","cited_by_count":11,"area":null},{"id":"2405.16714","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","created":"2024-05-26","cited_by_count":11,"area":null},{"id":"2410.13006","title":"LLM Chain Ensembles for Scalable and Accurate Data Annotation","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2504.13959","title":"AI Safety Should Prioritize the Future of Work","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2609.24574","title":"Evaluating Decision Models for Text Annotation in Computational Social Science","created":"2026-09-21","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":"2410.04501","title":"Leveraging Large Language Models for Suicide Detection on Social Media with Limited Labels","created":"2024-10-06","cited_by_count":10,"area":null},{"id":"2504.02767","title":"How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?","created":"2025-04-03","cited_by_count":10,"area":null},{"id":"2604.11581","title":"Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking","created":"2026-04-13","cited_by_count":10,"area":null},{"id":"2305.17561","title":"Grounding Characters and Places in Narrative Texts","created":"2023-05-27","cited_by_count":9,"area":null},{"id":"2404.10259","title":"Uncovering Latent Arguments in Social Media Messaging by Employing LLMs-in-the-Loop Strategy","created":"2024-04-16","cited_by_count":9,"area":null},{"id":"2410.12029","title":"On Classification with Large Language Models in Cultural Analytics","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2410.12327","title":"Neuron-based Personality Trait Induction in Large Language Models","created":"2024-10-16","cited_by_count":9,"area":null},{"id":"2509.16437","title":"SENSE-7: Taxonomy and Dataset for Measuring User Perceptions of Empathy in Sustained Human-AI Conversations","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2312.04578","title":"Towards a Psychological Generalist AI: A Survey of Current Applications of Large Language Models and Future Prospects","created":"2023-12-01","cited_by_count":8,"area":null},{"id":"2405.13052","title":"Large Language Models Can Infer Personality from Free-Form User Interactions","created":"2024-05-19","cited_by_count":8,"area":null},{"id":"2406.10942","title":"Effective Generative AI: The Human-Algorithm Centaur","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2407.09502","title":"From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2407.12814","title":"Computational Politeness in Natural Language Processing: A Survey","created":"2024-06-28","cited_by_count":8,"area":null},{"id":"2409.02078","title":"Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text","created":"2024-09-03","cited_by_count":8,"area":null},{"id":"2404.02261","title":"LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource Languages","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2408.01460","title":"LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models","created":"2024-07-27","cited_by_count":7,"area":null},{"id":"2505.19003","title":"Aligning LLM with human travel choices: a persona-based embedding learning approach","created":"2025-05-25","cited_by_count":7,"area":null},{"id":"2603.05923","title":"Learning Next Action Predictors from Human-Computer Interaction","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2606.19336","title":"Learning User Simulators with Turing Rewards","created":"2026-06-17","cited_by_count":7,"area":null},{"id":"2307.02763","title":"Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social Relationships","created":"2023-07-06","cited_by_count":6,"area":null},{"id":"2309.01659","title":"Evolving linguistic divergence on polarizing social media","created":"2023-09-04","cited_by_count":6,"area":null},{"id":"2406.11109","title":"Investigating Annotator Bias in Large Language Models for Hate Speech Detection","created":"2024-06-17","cited_by_count":6,"area":null},{"id":"2409.19750","title":"AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy","created":"2024-09-29","cited_by_count":6,"area":null},{"id":"2506.16702","title":"Large Language Models as Psychological Simulators: A Methodological Guide","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2510.01395","title":"Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2511.04195","title":"Computational Turing Test Reveals Systematic Differences Between Human and AI Language","created":"2025-11-06","cited_by_count":6,"area":null},{"id":"2305.14904","title":"Identifying Informational Sources in News Articles","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2312.16070","title":"Can ChatGPT Read Who You Are?","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2404.06731","title":"Accuracy of a Large Language Model in Distinguishing Anti- And Pro-vaccination Messages on Social Media: The Case of Human Papillomavirus Vaccination","created":"2024-04-10","cited_by_count":5,"area":null},{"id":"2409.18203","title":"Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2501.08413","title":"Labeling Free-text Data using Language Model Ensembles","created":"2025-01-14","cited_by_count":5,"area":null},{"id":"2504.00241","title":"Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacy","created":"2025-03-31","cited_by_count":5,"area":null},{"id":"2506.06390","title":"Benchmarking Large Language Models on Homework Assessment in Circuit Analysis","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2511.03235","title":"From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers","created":"2025-11-05","cited_by_count":5,"area":null},{"id":"2607.26348","title":"When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses","created":"2026-07-28","cited_by_count":5,"area":null}],"next_cursor":"100"}