{"ID":2876199,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00765","arxiv_id":"2509.00765","title":"Decomposing and Revising What Language Models Generate","abstract":"Attribution is crucial in question answering (QA) with Large Language Models (LLMs).SOTA question decomposition-based approaches use long form answers to generate questions for retrieving related documents. However, the generated questions are often irrelevant and incomplete, resulting in a loss of facts in retrieval.These approaches also fail to aggregate evidence snippets from different documents and paragraphs. To tackle these problems, we propose a new fact decomposition-based framework called FIDES (\\textit{faithful context enhanced fact decomposition and evidence aggregation}) for attributed QA. FIDES uses a contextually enhanced two-stage faithful decomposition method to decompose long form answers into sub-facts, which are then used by a retriever to retrieve related evidence snippets. If the retrieved evidence snippets conflict with the related sub-facts, such sub-facts will be revised accordingly. Finally, the evidence snippets are aggregated according to the original sentences.Extensive evaluation has been conducted with six datasets, with an additionally proposed new metric called $Attr_{auto-P}$ for evaluating the evidence precision. FIDES outperforms the SOTA methods by over 14\\% in average with GPT-3.5-turbo, Gemini and Llama 70B series.","short_abstract":"Attribution is crucial in question answering (QA) with Large Language Models (LLMs).SOTA question decomposition-based approaches use long form answers to generate questions for retrieving related documents. However, the generated questions are often irrelevant and incomplete, resulting in a loss of facts in retrieval.T...","url_abs":"https://arxiv.org/abs/2509.00765","url_pdf":"https://arxiv.org/pdf/2509.00765v1","authors":"[\"Zhichao Yan\",\"Jiaoyan Chen\",\"Jiapu Wang\",\"Xiaoli Li\",\"Ru Li\",\"Jeff Z. Pan\"]","published":"2025-08-31T09:26:25Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}