{"total":53,"rows":[{"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":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2303.04381","title":"Automatically Auditing Large Language Models via Discrete Optimization","created":"2023-03-08","cited_by_count":191,"area":null},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107,"area":null},{"id":"2202.12299","title":"Capturing Failures of Large Language Models via Human Cognitive Biases","created":"2022-02-24","cited_by_count":98,"area":null},{"id":"2102.00086","title":"Challenges in Automated Debiasing for Toxic Language Detection","created":"2021-01-29","cited_by_count":96,"area":null},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","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":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75,"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":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47,"area":null},{"id":"2601.17087","title":"Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations","created":"2026-01-23","cited_by_count":40,"area":"agents"},{"id":"2305.11242","title":"Comparing Biases and the Impact of Multilingual Training across Multiple Languages","created":"2023-05-18","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":"2502.13175","title":"Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks","created":"2025-02-18","cited_by_count":34,"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":"2305.12696","title":"Learning Interpretable Style Embeddings via Prompting LLMs","created":"2023-05-22","cited_by_count":30,"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":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2502.12858","title":"Rejected Dialects: Biases Against African American Language in Reward Models","created":"2025-02-18","cited_by_count":20,"area":"alignment"},{"id":"2101.00379","title":"Investigating Memorization of Conspiracy Theories in Text Generation","created":"2021-01-02","cited_by_count":15,"area":null},{"id":"2210.10329","title":"Language Detoxification with Attribute-Discriminative Latent Space","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2310.15398","title":"\"One-Size-Fits-All\"? Examining Expectations around What Constitute \"Fair\" or \"Good\" NLG System Behaviors","created":"2023-10-23","cited_by_count":11,"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":"2211.02882","title":"HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models","created":"2022-11-05","cited_by_count":8,"area":null},{"id":"2104.07874","title":"Translational NLP: A New Paradigm and General Principles for Natural Language Processing Research","created":"2021-04-16","cited_by_count":7,"area":null},{"id":"2205.06621","title":"Analyzing Hate Speech Data along Racial, Gender and Intersectional Axes","created":"2022-05-13","cited_by_count":7,"area":null},{"id":"2502.19721","title":"Unsupervised Concept Vector Extraction for Bias Control in LLMs","created":"2025-02-27","cited_by_count":7,"area":"mechinterp"},{"id":"2210.15500","title":"COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2406.08726","title":"Standard Language Ideology in AI-Generated Language","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2204.07289","title":"Identifying and Measuring Token-Level Sentiment Bias in Pre-trained Language Models with Prompts","created":"2022-04-15","cited_by_count":4,"area":null},{"id":"2512.15653","title":"Characterizing Mamba's Selective Memory using Auto-Encoders","created":"2025-12-17","cited_by_count":4,"area":"ssm"},{"id":"2206.08978","title":"Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American English","created":"2022-06-03","cited_by_count":3,"area":null},{"id":"2310.11079","title":"Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models","created":"2023-10-17","cited_by_count":3,"area":"safety"},{"id":"2503.10789","title":"Data Caricatures: On the Representation of African American Language in Pretraining Corpora","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2508.18288","title":"Toward Responsible ASR for African American English Speakers: A Scoping Review of Bias and Equity in Speech Technology","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2302.07324","title":"READIN: A Chinese Multi-Task Benchmark with Realistic and Diverse Input Noises","created":"2023-02-14","cited_by_count":1,"area":null},{"id":"2311.08472","title":"Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models","created":"2023-11-14","cited_by_count":1,"area":null},{"id":"2406.09977","title":"Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2407.12196","title":"MASIVE: Open-Ended Affective State Identification in English and Spanish","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2501.03441","title":"Finding A Voice: Exploring the Potential of African American Dialect and Voice Generation for Chatbots","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2509.17449","title":"SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2309.05668","title":"Studying the impacts of pre-training using ChatGPT-generated text on downstream tasks","created":"2023-09-02","cited_by_count":0,"area":null},{"id":"2502.07058","title":"Using Contextually Aligned Online Reviews to Measure LLMs' Performance Disparities Across Language Varieties","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2512.11505","title":"BAID: A Benchmark for Bias Assessment of AI Detectors","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.16398","title":"White-Box Sensitivity Auditing with Steering Vectors","created":"2026-01-23","cited_by_count":0,"area":"mechinterp"},{"id":"2603.15187","title":"The Hrunting of AI: Where and How to Improve English Dialectal Fairness","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.24384","title":"Side-by-side Comparison Amplifies Dialect Bias in Language Models","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.31741","title":"STEB: Style Text Embedding Benchmark","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.24952","title":"The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline","created":"2026-08-24","cited_by_count":0,"area":"mechinterp"},{"id":"2610.00164","title":"Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}