{"total":24,"rows":[{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"area":null},{"id":"2212.08620","title":"POTATO: The Portable Text Annotation Tool","created":"2022-12-16","cited_by_count":64,"area":null},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2305.13712","title":"Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models","created":"2023-05-23","cited_by_count":61,"area":null},{"id":"2306.06826","title":"When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2210.13001","title":"Modeling Information Change in Science Communication with Semantically Matched Paraphrases","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2406.03181","title":"Missci: Reconstructing Fallacies in Misrepresented Science","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2402.13109","title":"CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2402.14268","title":"Can Large Language Models Detect Misinformation in Scientific News Reporting?","created":"2024-02-22","cited_by_count":9,"area":null},{"id":"2402.12431","title":"Understanding Fine-grained Distortions in Reports of Scientific Findings","created":"2024-02-19","cited_by_count":8,"area":null},{"id":"2411.06528","title":"Epistemic Integrity in Large Language Models","created":"2024-11-10","cited_by_count":7,"area":null},{"id":"2402.10767","title":"Inference to the Best Explanation in Large Language Models","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2410.04981","title":"On the Rigour of Scientific Writing: Criteria, Analysis, and Insights","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2202.13610","title":"Did AI get more negative recently?","created":"2022-02-28","cited_by_count":4,"area":null},{"id":"2505.15031","title":"Are the confidence scores of reviewers consistent with the review content? Evidence from top conference proceedings in AI","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2601.04350","title":"RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2505.08143","title":"Communication styles and reader preferences of LLM- and human-authored COVID-19 information explanations: a case study","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2508.10927","title":"Modeling and Detecting Company Risks from News: A Case Study in Bloomberg News","created":"2025-08-10","cited_by_count":2,"area":null},{"id":"2512.19908","title":"Counterfactual LLM-based Framework for Measuring Rhetorical Style","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2410.19150","title":"A Test of Time: Predicting the Sustainable Success of Online Collaboration in Wikipedia","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2503.21114","title":"Measuring and Analyzing Subjective Uncertainty in Scientific Communications","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2506.16622","title":"Modeling Public Perceptions of Science in Media","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2606.07951","title":"From 'May' to 'Is': Certainty Distortion in Language Model Rewriting","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.21359","title":"Does Finetuning with Scientific Data Increase Hallucinations? A Multi-domain Factuality Evaluation of LLMs","created":"2026-06-19","cited_by_count":0,"area":null}],"next_cursor":null}