{"total":17,"rows":[{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613,"area":null},{"id":"2312.10523","title":"Paloma: A Benchmark for Evaluating Language Model Fit","created":"2023-12-16","cited_by_count":54,"area":null},{"id":"2311.14479","title":"Controlled Text Generation via Language Model Arithmetic","created":"2023-11-24","cited_by_count":51,"area":null},{"id":"2209.03463","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","created":"2022-09-07","cited_by_count":33,"area":null},{"id":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2212.06573","title":"On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning","created":"2022-12-13","cited_by_count":26,"area":null},{"id":"2311.01270","title":"People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection","created":"2023-11-02","cited_by_count":25,"area":null},{"id":"2311.12573","title":"Moderating Model Marketplaces: Platform Governance Puzzles for AI Intermediaries","created":"2023-11-21","cited_by_count":9,"area":null},{"id":"2306.03423","title":"I'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language Models","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2511.09292","title":"C$^3$TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2308.16549","title":"Thesis Distillation: Investigating The Impact of Bias in NLP Models on Hate Speech Detection","created":"2023-08-31","cited_by_count":2,"area":null},{"id":"2404.03048","title":"Decentralised Moderation for Interoperable Social Networks: A Conversation-based Approach for Pleroma and the Fediverse","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2503.11182","title":"Palette of Language Models: A Solver for Controlled Text Generation","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2306.15732","title":"A Weakly Supervised Classifier and Dataset of White Supremacist Language","created":"2023-06-27","cited_by_count":1,"area":null},{"id":"2504.00045","title":"Measuring Online Hate on 4chan using Pre-trained Deep Learning Models","created":"2025-03-30","cited_by_count":1,"area":null},{"id":"2411.13008","title":"Evaluating LLMs Capabilities Towards Understanding Social Dynamics","created":"2024-11-20","cited_by_count":0,"area":null}],"next_cursor":null}