{"work":{"id":"6d0d9d39-490d-48d5-b346-6bfe40b8b8fb","openalex_id":"https://openalex.org/W4401306838","doi":"10.48550/arxiv.2407.21772","arxiv_id":"2407.21772","raw_key":null,"title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","authors":null,"authors_text":"Wenjun Zeng, Yuchi Liu, Ryan Mullins, Ludovic Peran, Joe Fernandez, Hamza Harkous","year":2024,"venue":"cs.CL","abstract":"We present ShieldGemma, a comprehensive suite of LLM-based safety content moderation models built upon Gemma2. These models provide robust, state-of-the-art predictions of safety risks across key harm types (sexually explicit, dangerous content, harassment, hate speech) in both user input and LLM-generated output. By evaluating on both public and internal benchmarks, we demonstrate superior performance compared to existing models, such as Llama Guard (+10.8\\% AU-PRC on public benchmarks) and WildCard (+4.3\\%). Additionally, we present a novel LLM-based data curation pipeline, adaptable to a variety of safety-related tasks and beyond. We have shown strong generalization performance for model trained mainly on synthetic data. By releasing ShieldGemma, we provide a valuable resource to the research community, advancing LLM safety and enabling the creation of more effective content moderation solutions for developers.","external_url":"https://arxiv.org/abs/2407.21772","cited_by_count":2,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2407.21772","created_at":"2026-05-09T06:15:38.397958+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","render_title":"ShieldGemma: Generative AI Content Moderation Based on Gemma"},"hub":{"state":{"work_id":"6d0d9d39-490d-48d5-b346-6bfe40b8b8fb","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":53,"external_cited_by_count":2,"distinct_field_count":9,"first_pith_cited_at":"2025-02-03T11:02:30+00:00","last_pith_cited_at":"2026-07-07T14:25:05+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T02:49:25.321006+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}