{"total":202,"rows":[{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744,"area":null},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"area":"alignment"},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2208.10264","title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","created":"2022-08-18","cited_by_count":515,"area":null},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437,"area":null},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226,"area":"safety"},{"id":"2310.09219","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","created":"2023-10-13","cited_by_count":199,"area":null},{"id":"2210.17432","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","created":"2022-10-31","cited_by_count":194,"area":"diffusion"},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192,"area":null},{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143,"area":"alignment"},{"id":"2108.12084","title":"Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies","created":"2021-08-27","cited_by_count":128,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2403.18932","title":"Measuring Political Bias in Large Language Models: What Is Said and How It Is Said","created":"2024-03-27","cited_by_count":89,"area":null},{"id":"2106.14574","title":"Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics","created":"2021-06-28","cited_by_count":83,"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":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2205.12404","title":"FLUTE: Figurative Language Understanding through Textual Explanations","created":"2022-05-24","cited_by_count":79,"area":null},{"id":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77,"area":null},{"id":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76,"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":"2305.08379","title":"TESS: Text-to-Text Self-Conditioned Simplex Diffusion","created":"2023-05-15","cited_by_count":65,"area":"diffusion"},{"id":"2205.12558","title":"Gradient-Based Constrained Sampling from Language Models","created":"2022-05-25","cited_by_count":64,"area":null},{"id":"2402.01981","title":"Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes","created":"2024-02-03","cited_by_count":59,"area":null},{"id":"2208.01448","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","created":"2022-08-02","cited_by_count":57,"area":null},{"id":"2305.09941","title":"\"I'm fully who I am\": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation","created":"2023-05-17","cited_by_count":56,"area":null},{"id":"2209.12226","title":"Re-contextualizing Fairness in NLP: The Case of India","created":"2022-09-25","cited_by_count":55,"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":"2402.18050","title":"MEGAnno+: A Human-LLM Collaborative Annotation System","created":"2024-02-28","cited_by_count":47,"area":null},{"id":"2305.11080","title":"Inspecting the Geographical Representativeness of Images from Text-to-Image Models","created":"2023-05-18","cited_by_count":44,"area":"diffusion"},{"id":"2305.14889","title":"Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory","created":"2023-05-24","cited_by_count":43,"area":null},{"id":"2205.14219","title":"Controllable Text Generation with Neurally-Decomposed Oracle","created":"2022-05-27","cited_by_count":41,"area":null},{"id":"2203.12574","title":"Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal","created":"2022-03-23","cited_by_count":40,"area":"distill"},{"id":"2404.06345","title":"AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learning","created":"2024-04-09","cited_by_count":40,"area":"driving"},{"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":"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":"2310.05280","title":"Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems","created":"2023-10-08","cited_by_count":37,"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":"2202.08011","title":"Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks","created":"2022-02-16","cited_by_count":36,"area":null},{"id":"2305.14291","title":"Evaluation of African American Language Bias in Natural Language Generation","created":"2023-05-23","cited_by_count":36,"area":null},{"id":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","cited_by_count":33,"area":null},{"id":"2405.14191","title":"S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models","created":"2024-05-23","cited_by_count":33,"area":null},{"id":"2205.06828","title":"Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications","created":"2022-05-13","cited_by_count":32,"area":null},{"id":"2210.10837","title":"On Learning Fairness and Accuracy on Multiple Subgroups","created":"2022-10-19","cited_by_count":32,"area":null},{"id":"2403.20147","title":"IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context","created":"2024-03-29","cited_by_count":32,"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":"2311.00306","title":"Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation","created":"2023-11-01","cited_by_count":31,"area":null},{"id":"2402.06853","title":"History, Development, and Principles of Large Language Models-An Introductory Survey","created":"2024-02-10","cited_by_count":30,"area":null},{"id":"2502.13917","title":"TESS 2: A Large-Scale Generalist Diffusion Language Model","created":"2025-02-19","cited_by_count":30,"area":"diffusion"},{"id":"2405.20956","title":"A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedians","created":"2024-05-31","cited_by_count":29,"area":null},{"id":"2305.11262","title":"CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models","created":"2023-05-18","cited_by_count":28,"area":null},{"id":"2304.00958","title":"DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains","created":"2023-04-03","cited_by_count":27,"area":null},{"id":"2406.11107","title":"Exploring Safety-Utility Trade-Offs in Personalized Language Models","created":"2024-06-17","cited_by_count":27,"area":null},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26,"area":null},{"id":"2406.01285","title":"Large Language Models as Recommender Systems: A Study of Popularity Bias","created":"2024-06-03","cited_by_count":26,"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":"2410.12864","title":"Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs","created":"2024-10-13","cited_by_count":25,"area":null},{"id":"2301.09211","title":"An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models","created":"2023-01-22","cited_by_count":24,"area":null},{"id":"2501.19392","title":"Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models","created":"2025-01-31","cited_by_count":24,"area":"inference"},{"id":"2211.02069","title":"LMentry: A Language Model Benchmark of Elementary Language Tasks","created":"2022-11-03","cited_by_count":22,"area":null},{"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":"2309.08836","title":"Bias and Fairness in Chatbots: An Overview","created":"2023-09-16","cited_by_count":20,"area":null},{"id":"2310.05294","title":"Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with the GeNTE Corpus","created":"2023-10-08","cited_by_count":20,"area":null},{"id":"2406.19097","title":"Fairness and Bias in Multimodal AI: A Survey","created":"2024-06-27","cited_by_count":20,"area":"mllm"},{"id":"2505.21819","title":"Representative Language Generation","created":"2025-05-27","cited_by_count":19,"area":null},{"id":"2210.07455","title":"Controlling Bias Exposure for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2503.00596","title":"BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge","created":"2025-03-01","cited_by_count":18,"area":"safety"},{"id":"2305.19821","title":"LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting","created":"2023-05-31","cited_by_count":17,"area":"rag"},{"id":"2407.15366","title":"Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2501.14844","title":"Unmasking Conversational Bias in AI Multiagent Systems","created":"2025-01-24","cited_by_count":17,"area":null},{"id":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16,"area":null},{"id":"2109.07465","title":"On the Limits of Minimal Pairs in Contrastive Evaluation","created":"2021-09-15","cited_by_count":15,"area":null},{"id":"2310.14777","title":"Geographical Erasure in Language Generation","created":"2023-10-23","cited_by_count":15,"area":null},{"id":"2410.00545","title":"What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study","created":"2024-10-01","cited_by_count":15,"area":null},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2305.11140","title":"Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2404.12744","title":"Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches","created":"2024-04-19","cited_by_count":14,"area":null},{"id":"2305.17696","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2408.11843","title":"Identifying and Mitigating Social Bias Knowledge in Language Models","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2505.18154","title":"The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2109.04624","title":"Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness","created":"2021-09-10","cited_by_count":12,"area":null},{"id":"2205.11485","title":"Conditional Supervised Contrastive Learning for Fair Text Classification","created":"2022-05-23","cited_by_count":11,"area":null},{"id":"2305.05364","title":"Large Language Model Programs","created":"2023-05-09","cited_by_count":11,"area":null},{"id":"2410.19109","title":"RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2412.06483","title":"SafeWorld: Geo-Diverse Safety Alignment","created":"2024-12-09","cited_by_count":11,"area":"wm"},{"id":"2505.13487","title":"Detecting Prefix Bias in LLM-based Reward Models","created":"2025-05-13","cited_by_count":11,"area":"alignment"},{"id":"2210.07382","title":"Behavior Cloned Transformers are Neurosymbolic Reasoners","created":"2022-10-13","cited_by_count":10,"area":null},{"id":"2305.17627","title":"Robust Natural Language Understanding with Residual Attention Debiasing","created":"2023-05-28","cited_by_count":10,"area":null},{"id":"2309.07689","title":"Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Text","created":"2023-09-14","cited_by_count":10,"area":null}],"next_cursor":"100"}