{"total":30,"rows":[{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199,"area":null},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2306.11507","title":"TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models","created":"2023-06-20","cited_by_count":58,"area":null},{"id":"2305.04446","title":"Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks","created":"2023-05-08","cited_by_count":46,"area":null},{"id":"2305.09067","title":"SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting","created":"2023-05-15","cited_by_count":39,"area":null},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2405.06996","title":"Quite Good, but Not Enough: Nationality Bias in Large Language Models -- A Case Study of ChatGPT","created":"2024-05-11","cited_by_count":13,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2507.07640","title":"Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement","created":"2025-07-10","cited_by_count":10,"area":null},{"id":"2203.17090","title":"PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2305.02626","title":"\"Oops, Did I Just Say That?\" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process","created":"2023-05-04","cited_by_count":9,"area":null},{"id":"2501.15451","title":"STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2402.14258","title":"Eagle: Ethical Dataset Given from Real Interactions","created":"2024-02-22","cited_by_count":4,"area":null},{"id":"2402.14889","title":"COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2409.15766","title":"CHBench: A Chinese Dataset for Evaluating Health in Large Language Models","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2411.19668","title":"ChineseWebText 2.0: Large-Scale High-quality Chinese Web Text with Multi-dimensional and fine-grained information","created":"2024-11-29","cited_by_count":3,"area":null},{"id":"2310.03283","title":"A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2501.00697","title":"PANDA -- Paired Anti-hate Narratives Dataset from Asia: Using an LLM-as-a-Judge to Create the First Chinese Counterspeech Dataset","created":"2025-01-01","cited_by_count":2,"area":null},{"id":"2505.15297","title":"Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.11292","title":"Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2508.11278","title":"Is General-Purpose AI Reasoning Sensitive to Data-Induced Cognitive Biases? Dynamic Benchmarking on Typical Software Engineering Dilemmas","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2508.20201","title":"Social Bias in Multilingual Language Models: A Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2309.08624","title":"Challenges in Annotating Datasets to Quantify Bias in Under-represented Society","created":"2023-09-11","cited_by_count":1,"area":null},{"id":"2408.01935","title":"Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2505.22184","title":"Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2404.08666","title":"Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences","created":"2024-03-31","cited_by_count":0,"area":null},{"id":"2512.00556","title":"Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2606.27629","title":"Cross-Platform Chinese Offensive Comment Detection via Dual-Threshold Hard Example Mining","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2609.01611","title":"EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}