{"total":83,"rows":[{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019,"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":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"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":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422,"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":"2301.01768","title":"The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation","created":"2023-01-05","cited_by_count":189,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181,"area":null},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115,"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":"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":"2111.07408","title":"Time Waits for No One! Analysis and Challenges of Temporal Misalignment","created":"2021-11-14","cited_by_count":91,"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":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"area":null},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73,"area":null},{"id":"2202.04173","title":"Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models","created":"2022-02-08","cited_by_count":68,"area":null},{"id":"2203.13299","title":"Mix and Match: Learning-free Controllable Text Generation using Energy Language Models","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"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":"2407.14933","title":"Consent in Crisis: The Rapid Decline of the AI Data Commons","created":"2024-07-20","cited_by_count":46,"area":null},{"id":"2303.01325","title":"A Pathway Towards Responsible AI Generated Content","created":"2023-03-02","cited_by_count":38,"area":null},{"id":"2212.10543","title":"Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts","created":"2022-12-20","cited_by_count":36,"area":null},{"id":"2305.08005","title":"Beyond the Safeguards: Exploring the Security Risks of ChatGPT","created":"2023-05-13","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":"2405.02774","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","created":"2024-05-05","cited_by_count":32,"area":null},{"id":"2307.08925","title":"Integration of Large Language Models and Federated Learning","created":"2023-07-18","cited_by_count":31,"area":null},{"id":"2307.03214","title":"PREADD: Prefix-Adaptive Decoding for Controlled Text Generation","created":"2023-07-06","cited_by_count":29,"area":null},{"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":"2402.15350","title":"Farsight: Fostering Responsible AI Awareness During AI Application Prototyping","created":"2024-02-23","cited_by_count":28,"area":null},{"id":"2210.03070","title":"Toxicity in Multilingual Machine Translation at Scale","created":"2022-10-06","cited_by_count":26,"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":"2401.14362","title":"The Typing Cure: Experiences with Large Language Model Chatbots for Mental Health Support","created":"2024-01-25","cited_by_count":24,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2203.03072","title":"Leashing the Inner Demons: Self-Detoxification for Language Models","created":"2022-03-06","cited_by_count":19,"area":null},{"id":"2212.10466","title":"Controllable Text Generation with Language Constraints","created":"2022-12-20","cited_by_count":18,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2302.07388","title":"Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2302.14003","title":"Systematic Rectification of Language Models via Dead-end Analysis","created":"2023-02-27","cited_by_count":16,"area":null},{"id":"2406.00020","title":"Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2407.09241","title":"The Sociolinguistic Foundations of Language Modeling","created":"2024-07-12","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2204.05151","title":"Metaethical Perspectives on 'Benchmarking' AI Ethics","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2311.11415","title":"A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models","created":"2023-11-19","cited_by_count":12,"area":null},{"id":"2210.10329","title":"Language Detoxification with Attribute-Discriminative Latent Space","created":"2022-10-19","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":"2407.06380","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","created":"2024-07-08","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":"2306.00198","title":"An Invariant Learning Characterization of Controlled Text Generation","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2407.14259","title":"Voices in a Crowd: Searching for Clusters of Unique Perspectives","created":"2024-07-19","cited_by_count":9,"area":null},{"id":"2306.00374","title":"CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2308.08295","title":"CMD: a framework for Context-aware Model self-Detoxification","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2312.04510","title":"A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2412.14050","title":"Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2210.07595","title":"The State of Profanity Obfuscation in Natural Language Processing","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2305.14757","title":"Psychological Metrics for Dialog System Evaluation","created":"2023-05-24","cited_by_count":4,"area":null},{"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":"2312.06122","title":"GTA: Gated Toxicity Avoidance for LM Performance Preservation","created":"2023-12-11","cited_by_count":3,"area":null},{"id":"2406.00548","title":"LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2504.00695","title":"ToReMi: Topic-Aware Data Reweighting for Dynamic Pre-Training Data Selection","created":"2025-04-01","cited_by_count":3,"area":null},{"id":"2505.16722","title":"Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2506.05635","title":"IYKYK: Using language models to decode extremist cryptolects","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2604.14602","title":"CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2304.14553","title":"Appropriateness is all you need!","created":"2023-04-27","cited_by_count":2,"area":null},{"id":"2408.12806","title":"Is Generative AI the Next Tactical Cyber Weapon For Threat Actors? Unforeseen Implications of AI Generated Cyber Attacks","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2506.06238","title":"Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detection","created":"2025-06-06","cited_by_count":2,"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":"2311.11229","title":"Causal ATE Mitigates Unintended Bias in Controlled Text Generation","created":"2023-11-19","cited_by_count":1,"area":null},{"id":"2401.08491","title":"Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2406.13660","title":"Towards Minimal Targeted Updates of Language Models with Targeted Negative Training","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2408.13278","title":"Randomization Techniques to Mitigate the Risk of Copyright Infringement","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2410.19812","title":"Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2601.08668","title":"Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2203.11401","title":"Suum Cuique: Studying Bias in Taboo Detection with a Community Perspective","created":"2022-03-22","cited_by_count":0,"area":null},{"id":"2304.11223","title":"A Group-Specific Approach to NLP for Hate Speech Detection","created":"2023-04-21","cited_by_count":0,"area":null},{"id":"2403.14467","title":"Recourse for reclamation: Chatting with generative language models","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2601.18127","title":"The Limits of AI Data Transparency Policy: Three Disclosure Fallacies","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.28351","title":"Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2609.20779","title":"Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}