{"work":{"id":"1820f37c-e2c1-4f5c-81b1-3b81aa324cab","openalex_id":null,"doi":null,"arxiv_id":"2309.15217","raw_key":null,"title":"Ragas: Automated Evaluation of Retrieval Augmented Generation","authors":null,"authors_text":"Shahul Es, Jithin James, Luis Espinosa-Anke, Steven Schockaert","year":2023,"venue":"cs.CL","abstract":"We introduce Ragas (Retrieval Augmented Generation Assessment), a framework for reference-free evaluation of Retrieval Augmented Generation (RAG) pipelines. RAG systems are composed of a retrieval and an LLM based generation module, and provide LLMs with knowledge from a reference textual database, which enables them to act as a natural language layer between a user and textual databases, reducing the risk of hallucinations. Evaluating RAG architectures is, however, challenging because there are several dimensions to consider: the ability of the retrieval system to identify relevant and focused context passages, the ability of the LLM to exploit such passages in a faithful way, or the quality of the generation itself. With Ragas, we put forward a suite of metrics which can be used to evaluate these different dimensions \\textit{without having to rely on ground truth human annotations}. We posit that such a framework can crucially contribute to faster evaluation cycles of RAG architectures, which is especially important given the fast adoption of LLMs.","external_url":"https://arxiv.org/abs/2309.15217","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T08:15:33.905536+00:00","pith_arxiv_id":"2309.15217","created_at":"2026-05-10T04:04:47.603539+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Ragas: Automated Evaluation of Retrieval Augmented Generation","render_title":"Ragas: Automated Evaluation of Retrieval Augmented Generation"},"hub":{"state":{"work_id":"1820f37c-e2c1-4f5c-81b1-3b81aa324cab","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":24,"external_cited_by_count":null,"distinct_field_count":6,"first_pith_cited_at":"2023-12-18T07:47:33+00:00","last_pith_cited_at":"2026-05-18T20:01:05+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":"2026-06-06T18:00:57.050534+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":6}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"unclear","n":2},{"context_polarity":"support","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}