{"ID":2837706,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19349","arxiv_id":"2511.19349","title":"Revisiting Feedback Models for HyDE","abstract":"Recent approaches that leverage large language models (LLMs) for pseudo-relevance feedback (PRF) have generally not utilized well-established feedback models like Rocchio and RM3 when expanding queries for sparse retrievers like BM25. Instead, they often opt for a simple string concatenation of the query and LLM-generated expansion content. But is this optimal? To answer this question, we revisit and systematically evaluate traditional feedback models in the context of HyDE, a popular method that enriches query representations with LLM-generated hypothetical answer documents. Our experiments show that HyDE's effectiveness can be substantially improved when leveraging feedback algorithms such as Rocchio to extract and weight expansion terms, providing a simple way to further enhance the accuracy of LLM-based PRF methods.","short_abstract":"Recent approaches that leverage large language models (LLMs) for pseudo-relevance feedback (PRF) have generally not utilized well-established feedback models like Rocchio and RM3 when expanding queries for sparse retrievers like BM25. Instead, they often opt for a simple string concatenation of the query and LLM-genera...","url_abs":"https://arxiv.org/abs/2511.19349","url_pdf":"https://arxiv.org/pdf/2511.19349v1","authors":"[\"Nour Jedidi\",\"Jimmy Lin\"]","published":"2025-11-24T17:50:18Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}