{"total":18,"rows":[{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50,"area":null},{"id":"2405.02750","title":"Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding","created":"2024-05-04","cited_by_count":49,"area":null},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2402.11218","title":"Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs","created":"2024-02-17","cited_by_count":16,"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":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2404.10464","title":"DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion","created":"2024-04-16","cited_by_count":9,"area":null},{"id":"2408.08291","title":"The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community","created":"2024-08-15","cited_by_count":8,"area":null},{"id":"2504.20500","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2506.01790","title":"IF-GUIDE: Influence Function-Guided Detoxification of LLMs","created":"2025-06-02","cited_by_count":7,"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":"2404.07135","title":"Towards Robustness of Text-to-Visualization Translation against Lexical and Phrasal Variability","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2501.15758","title":"Distributional Surgery for Language Model Activations","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2506.02326","title":"Something Just Like TRuST : Toxicity Recognition of Span and Target","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2402.15202","title":"Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2607.23175","title":"Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining","created":"2026-07-25","cited_by_count":0,"area":null}],"next_cursor":null}