{"total":144,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028,"area":null},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626,"area":null},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870,"area":null},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734,"area":null},{"id":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422,"area":null},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390,"area":null},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"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":"2304.11633","title":"Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness","created":"2023-04-23","cited_by_count":130,"area":null},{"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":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2310.20410","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","created":"2023-10-31","cited_by_count":117,"area":null},{"id":"2310.15638","title":"CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation","created":"2023-10-24","cited_by_count":94,"area":null},{"id":"2304.10145","title":"Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks","created":"2023-04-20","cited_by_count":89,"area":null},{"id":"2303.07992","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","created":"2023-03-14","cited_by_count":71,"area":null},{"id":"2312.02913","title":"Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions","created":"2023-12-05","cited_by_count":70,"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":"2304.11085","title":"Testing the Reliability of ChatGPT for Text Annotation and Classification: A Cautionary Remark","created":"2023-04-17","cited_by_count":54,"area":null},{"id":"2310.12860","title":"Probing LLMs for hate speech detection: strengths and vulnerabilities","created":"2023-10-19","cited_by_count":52,"area":null},{"id":"2401.01523","title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse","created":"2024-01-03","cited_by_count":52,"area":null},{"id":"2405.03371","title":"Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom","created":"2024-05-06","cited_by_count":50,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2303.03953","title":"ChatGPT: Beginning of an End of Manual Linguistic Data Annotation? Use Case of Automatic Genre Identification","created":"2023-03-07","cited_by_count":45,"area":null},{"id":"2304.12008","title":"CHEAT: A Large-scale Dataset for Detecting ChatGPT-writtEn AbsTracts","created":"2023-04-24","cited_by_count":40,"area":null},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2402.16795","title":"If in a Crowdsourced Data Annotation Pipeline, a GPT-4","created":"2024-02-26","cited_by_count":38,"area":null},{"id":"2401.07103","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","created":"2024-01-13","cited_by_count":37,"area":null},{"id":"2408.03907","title":"Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models","created":"2024-08-07","cited_by_count":33,"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":"2305.10235","title":"Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility","created":"2023-05-15","cited_by_count":30,"area":null},{"id":"2409.03219","title":"Content Moderation by LLM: From Accuracy to Legitimacy","created":"2024-09-05","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":"2405.01299","title":"The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation","created":"2024-05-02","cited_by_count":29,"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":"2402.00371","title":"What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection","created":"2024-02-01","cited_by_count":25,"area":null},{"id":"2402.11406","title":"Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection","created":"2024-02-18","cited_by_count":25,"area":null},{"id":"2410.02657","title":"Hate Personified: Investigating the role of LLMs in content moderation","created":"2024-10-03","cited_by_count":25,"area":null},{"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":"2405.05253","title":"Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge","created":"2024-05-08","cited_by_count":20,"area":null},{"id":"2406.12114","title":"Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation","created":"2024-06-17","cited_by_count":20,"area":null},{"id":"2310.09223","title":"Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation","created":"2023-10-13","cited_by_count":19,"area":null},{"id":"2311.09812","title":"Large Language Models for Propaganda Span Annotation","created":"2023-11-16","cited_by_count":19,"area":null},{"id":"2307.14107","title":"Decoding ChatGPT: A Taxonomy of Existing Research, Current Challenges, and Possible Future Directions","created":"2023-07-26","cited_by_count":18,"area":null},{"id":"2403.18152","title":"Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency","created":"2024-03-26","cited_by_count":18,"area":null},{"id":"2310.05046","title":"FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models","created":"2023-10-08","cited_by_count":17,"area":null},{"id":"2310.05657","title":"A Closer Look into Automatic Evaluation Using Large Language Models","created":"2023-10-09","cited_by_count":17,"area":null},{"id":"2310.15144","title":"DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2403.17368","title":"ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?","created":"2024-03-26","cited_by_count":17,"area":null},{"id":"2409.09467","title":"Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI","created":"2024-09-14","cited_by_count":17,"area":null},{"id":"2406.11980","title":"Prompt Design Matters for Computational Social Science Tasks but in Unpredictable Ways","created":"2024-06-17","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":"2401.15498","title":"Do We Need Language-Specific Fact-Checking Models? The Case of Chinese","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2404.17475","title":"CEval: A Benchmark for Evaluating Counterfactual Text Generation","created":"2024-04-26","cited_by_count":15,"area":null},{"id":"2405.11290","title":"MBIAS: Mitigating Bias in Large Language Models While Retaining Context","created":"2024-05-18","cited_by_count":15,"area":null},{"id":"2411.11081","title":"The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection","created":"2024-11-17","cited_by_count":15,"area":null},{"id":"2305.14556","title":"Unraveling ChatGPT: A Critical Analysis of AI-Generated Goal-Oriented Dialogues and Annotations","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2309.17447","title":"A Large Language Model Approach to Educational Survey Feedback Analysis","created":"2023-09-29","cited_by_count":14,"area":null},{"id":"2502.06207","title":"Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2308.13577","title":"Text Style Transfer Evaluation Using Large Language Models","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2312.00819","title":"Large Language Models for Travel Behavior Prediction","created":"2023-11-30","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":"2304.02017","title":"Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing","created":"2023-03-27","cited_by_count":11,"area":null},{"id":"2307.04251","title":"ChatGPT in the Age of Generative AI and Large Language Models: A Concise Survey","created":"2023-07-09","cited_by_count":10,"area":null},{"id":"2312.10321","title":"LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?","created":"2023-12-16","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":"2309.10463","title":"Exploring the Dark Side of AI: Advanced Phishing Attack Design and Deployment Using ChatGPT","created":"2023-09-19","cited_by_count":9,"area":null},{"id":"2409.10527","title":"Towards Empathetic Conversational Recommender Systems","created":"2024-08-30","cited_by_count":9,"area":null},{"id":"2309.06503","title":"Leveraging Large Language Models and Weak Supervision for Social Media data annotation: an evaluation using COVID-19 self-reported vaccination tweets","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2405.00390","title":"CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models","created":"2024-05-01","cited_by_count":8,"area":null},{"id":"2502.16550","title":"PropXplain: Can LLMs Enable Explainable Propaganda Detection?","created":"2025-02-23","cited_by_count":8,"area":null},{"id":"2304.12479","title":"AGI: Artificial General Intelligence for Education","created":"2023-04-24","cited_by_count":7,"area":null},{"id":"2402.01681","title":"Emojis Decoded: Leveraging ChatGPT for Enhanced Understanding in Social Media Communications","created":"2024-01-22","cited_by_count":7,"area":null},{"id":"2411.08977","title":"Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness","created":"2024-11-13","cited_by_count":7,"area":null},{"id":"2501.15042","title":"SCCD: A Session-based Dataset for Chinese Cyberbullying Detection","created":"2025-01-25","cited_by_count":7,"area":null},{"id":"2505.06149","title":"Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study","created":"2025-05-09","cited_by_count":7,"area":null},{"id":"2601.21817","title":"A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2305.13276","title":"Evaluating ChatGPT's Performance for Multilingual and Emoji-based Hate Speech Detection","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2307.12973","title":"Wisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation","created":"2023-07-24","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":"2310.15055","title":"Towards Conceptualization of \"Fair Explanation\": Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2401.17839","title":"Global-Liar: Factuality of LLMs over Time and Geographic Regions","created":"2024-01-31","cited_by_count":6,"area":null},{"id":"2407.04130","title":"Towards Automating Text Annotation: A Case Study on Semantic Proximity Annotation using GPT-4","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2406.10249","title":"A Reality check of the benefits of LLM in business","created":"2024-06-09","cited_by_count":5,"area":null},{"id":"2407.02977","title":"Large Language Models as Evaluators for Scientific Synthesis","created":"2024-07-03","cited_by_count":5,"area":null},{"id":"2410.15623","title":"Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2503.05049","title":"Dynamic-KGQA: A Scalable Framework for Generating Adaptive Question Answering Datasets","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2504.04299","title":"AI-induced sexual harassment: Investigating Contextual Characteristics and User Reactions of Sexual Harassment by a Companion Chatbot","created":"2025-04-05","cited_by_count":5,"area":null},{"id":"2310.20153","title":"Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2403.08035","title":"Harnessing Artificial Intelligence to Combat Online Hate: Exploring the Challenges and Opportunities of Large Language Models in Hate Speech Detection","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2404.17985","title":"Detection of Conspiracy Theories Beyond Keyword Bias in German-Language Telegram Using Large Language Models","created":"2024-04-27","cited_by_count":4,"area":null},{"id":"2407.11827","title":"GPT Assisted Annotation of Rhetorical and Linguistic Features for Interpretable Propaganda Technique Detection in News Text","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2503.04874","title":"Memory Is All You Need: Testing How Model Memory Affects LLM Performance in Annotation Tasks","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2305.12152","title":"Revisiting Automated Topic Model Evaluation with Large Language Models","created":"2023-05-20","cited_by_count":3,"area":null},{"id":"2403.02472","title":"OffensiveLang: A Community Based Implicit Offensive Language Dataset","created":"2024-03-04","cited_by_count":3,"area":null},{"id":"2406.16349","title":"AnnotatedTables: A Large Tabular Dataset with Language Model Annotations","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2409.10702","title":"Model-in-the-Loop (MILO): Accelerating Multimodal AI Data Annotation with LLMs","created":"2024-09-16","cited_by_count":3,"area":null},{"id":"2411.17204","title":"Strategic Prompting for Conversational Tasks: A Comparative Analysis of Large Language Models Across Diverse Conversational Tasks","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2305.14658","title":"Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2312.03726","title":"Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2402.13372","title":"EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries","created":"2024-02-20","cited_by_count":2,"area":null}],"next_cursor":"100"}