{"total":126,"rows":[{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897,"area":"wm"},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701,"area":null},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492,"area":null},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348,"area":null},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2311.04892","title":"Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs","created":"2023-11-08","cited_by_count":199,"area":"lr"},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2402.02680","title":"Large Language Models are Geographically Biased","created":"2024-02-05","cited_by_count":93,"area":"wm"},{"id":"2306.05949","title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","created":"2023-06-09","cited_by_count":92,"area":null},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"area":null},{"id":"2503.16527","title":"LLM Generated Persona is a Promise with a Catch","created":"2025-03-18","cited_by_count":81,"area":null},{"id":"2401.12242","title":"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models","created":"2024-01-20","cited_by_count":80,"area":"lr"},{"id":"2306.07951","title":"Questioning the Survey Responses of Large Language Models","created":"2023-06-13","cited_by_count":74,"area":null},{"id":"2307.16778","title":"KoBBQ: Korean Bias Benchmark for Question Answering","created":"2023-07-31","cited_by_count":71,"area":null},{"id":"2405.13401","title":"TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models","created":"2024-05-22","cited_by_count":67,"area":"rag"},{"id":"2305.11840","title":"SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models","created":"2023-05-19","cited_by_count":66,"area":null},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"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":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49,"area":null},{"id":"2106.01465","title":"Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?","created":"2021-06-02","cited_by_count":46,"area":null},{"id":"2109.02593","title":"General-Purpose Question-Answering with Macaw","created":"2021-09-06","cited_by_count":40,"area":null},{"id":"2407.03129","title":"Social Bias Evaluation for Large Language Models Requires Prompt Variations","created":"2024-07-03","cited_by_count":40,"area":null},{"id":"2504.14492","title":"FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering","created":"2025-04-20","cited_by_count":40,"area":"mechinterp"},{"id":"2210.04337","title":"Quantifying Social Biases Using Templates is Unreliable","created":"2022-10-09","cited_by_count":39,"area":null},{"id":"2410.19317","title":"FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs","created":"2024-10-25","cited_by_count":36,"area":null},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35,"area":null},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2407.04965","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31,"area":null},{"id":"2103.11320","title":"Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources","created":"2021-03-21","cited_by_count":30,"area":null},{"id":"2109.10441","title":"Evaluating Debiasing Techniques for Intersectional Biases","created":"2021-09-21","cited_by_count":30,"area":null},{"id":"2501.17420","title":"Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models","created":"2025-01-29","cited_by_count":30,"area":"agents"},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"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":"2410.14012","title":"LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education","created":"2024-10-17","cited_by_count":28,"area":null},{"id":"2409.19804","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","created":"2024-09-29","cited_by_count":26,"area":"rag"},{"id":"2307.10514","title":"Building Socio-culturally Inclusive Stereotype Resources with Community Engagement","created":"2023-07-20","cited_by_count":25,"area":null},{"id":"2305.17701","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","created":"2023-05-28","cited_by_count":24,"area":null},{"id":"2306.16244","title":"CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2023-06-28","cited_by_count":23,"area":null},{"id":"2210.07269","title":"SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models","created":"2022-10-13","cited_by_count":22,"area":"lr"},{"id":"2407.10241","title":"BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs","created":"2024-07-14","cited_by_count":21,"area":null},{"id":"2211.07886","title":"A Survey for Efficient Open Domain Question Answering","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2502.01926","title":"Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs","created":"2025-02-04","cited_by_count":20,"area":null},{"id":"2502.11767","title":"From Selection to Generation: A Survey of LLM-based Active Learning","created":"2025-02-17","cited_by_count":19,"area":null},{"id":"2403.13213","title":"From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards","created":"2024-03-20","cited_by_count":17,"area":null},{"id":"2108.01764","title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","created":"2021-08-03","cited_by_count":16,"area":null},{"id":"2410.17519","title":"Large Language Models Still Exhibit Bias in Long Text","created":"2024-10-23","cited_by_count":16,"area":null},{"id":"2402.15481","title":"Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency","created":"2024-02-23","cited_by_count":15,"area":null},{"id":"2308.12539","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2406.04064","title":"Ask LLMs Directly, \"What shapes your bias?\": Measuring Social Bias in Large Language Models","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2305.16577","title":"Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name Biases","created":"2023-05-26","cited_by_count":12,"area":null},{"id":"2411.07237","title":"Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries","created":"2024-11-11","cited_by_count":12,"area":null},{"id":"2202.10848","title":"Speciesist bias in AI -- How AI applications perpetuate discrimination and unfair outcomes against animals","created":"2022-02-22","cited_by_count":11,"area":null},{"id":"2203.06342","title":"What Makes Reading Comprehension Questions Difficult?","created":"2022-03-12","cited_by_count":11,"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":"2402.12150","title":"Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One","created":"2024-02-19","cited_by_count":11,"area":null},{"id":"2205.11605","title":"On Measuring Social Biases in Prompt-Based Multi-Task Learning","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2412.06134","title":"Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings","created":"2024-12-09","cited_by_count":10,"area":null},{"id":"2305.12757","title":"This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2407.10853","title":"Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMs","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2506.23111","title":"FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes","created":"2025-06-29","cited_by_count":9,"area":null},{"id":"2310.08795","title":"Mitigating Bias for Question Answering Models by Tracking Bias Influence","created":"2023-10-13","cited_by_count":8,"area":null},{"id":"2412.13835","title":"RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs","created":"2024-12-18","cited_by_count":8,"area":null},{"id":"2303.00673","title":"Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness","created":"2023-03-01","cited_by_count":7,"area":null},{"id":"2406.02050","title":"JBBQ: Japanese Bias Benchmark for Analyzing Social Biases in Large Language Models","created":"2024-06-04","cited_by_count":7,"area":null},{"id":"2409.11579","title":"HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2104.07571","title":"Toward Deconfounding the Influence of Entity Demographics for Question Answering Accuracy","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2205.15951","title":"Hollywood Identity Bias Dataset: A Context Oriented Bias Analysis of Movie Dialogues","created":"2022-05-31","cited_by_count":5,"area":null},{"id":"2302.05508","title":"FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models","created":"2023-02-10","cited_by_count":5,"area":null},{"id":"2405.06687","title":"Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes","created":"2024-05-06","cited_by_count":5,"area":null},{"id":"2407.21058","title":"Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT","created":"2024-07-25","cited_by_count":5,"area":null},{"id":"2501.03112","title":"LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases","created":"2025-01-06","cited_by_count":5,"area":null},{"id":"2503.04372","title":"Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2503.15815","title":"Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2512.23430","title":"C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2212.07877","title":"Manifestations of Xenophobia in AI Systems","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2311.09741","title":"P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models","created":"2023-11-16","cited_by_count":4,"area":"diffusion"},{"id":"2403.04858","title":"Evaluating Biases in Context-Dependent Health Questions","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2406.12347","title":"Interpreting Bias in Large Language Models: A Feature-Based Approach","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2412.12300","title":"Unanswerability Evaluation for Retrieval Augmented Generation","created":"2024-12-16","cited_by_count":4,"area":"rag"},{"id":"2503.11985","title":"No LLM is Free From Bias: A Comprehensive Study of Bias Evaluation in Large Language Models","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2504.21299","title":"BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models","created":"2025-04-30","cited_by_count":4,"area":"lr"},{"id":"2508.10186","title":"PakBBQ: A Culturally Adapted Bias Benchmark for QA","created":"2025-08-13","cited_by_count":4,"area":null},{"id":"2209.07760","title":"Possible Stories: Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios","created":"2022-09-16","cited_by_count":3,"area":"lr"},{"id":"2409.17827","title":"BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2506.05390","title":"Understanding Gender Bias in AI-Generated Product Descriptions","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2507.16557","title":"Exploring Gender Bias in Large Language Models: An In-depth Dive into the German Language","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2604.08243","title":"Self-Debias: Self-correcting for Debiasing Large Language Models","created":"2026-04-09","cited_by_count":3,"area":"lr"},{"id":"2203.05140","title":"Speciesist Language and Nonhuman Animal Bias in English Masked Language Models","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2308.06686","title":"TorchQL: A Programming Framework for Integrity Constraints in Machine Learning","created":"2023-08-13","cited_by_count":2,"area":null}],"next_cursor":"100"}