{"total":15,"rows":[{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2506.06347","title":"Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection","created":"2025-06-01","cited_by_count":5,"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":"2508.11281","title":"ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2509.25539","title":"Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2606.07874","title":"Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2601.09250","title":"When to Invoke: Refining LLM Fairness with Toxicity Assessment","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2509.09043","title":"Stated Preference for Interaction and Continued Engagement (SPICE): Evaluating an LLM's Willingness to Re-engage in Conversation","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2510.08236","title":"The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2604.19124","title":"Detoxification for LLM: From Dataset Itself","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.24000","title":"Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.09700","title":"What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.17506","title":"Evaluating Second-Order Bias of LLMs Through Epistemic Entitlement","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2609.20059","title":"AI Should Facilitate Democratic Deliberation at Scale","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}