Revisiting Feedback Models for HyDE

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jedidi, Nour, Lin, Jimmy
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918216616378368
author Jedidi, Nour
Lin, Jimmy
author_facet Jedidi, Nour
Lin, Jimmy
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19349
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Revisiting Feedback Models for HyDE
Jedidi, Nour
Lin, Jimmy
Information Retrieval
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.
title Revisiting Feedback Models for HyDE
topic Information Retrieval
url https://arxiv.org/abs/2511.19349