Metraipolis › archive › dc_519b58efcec8

Learning Multi-Step Query Rewriting via Corpus Feedback for Conversational Search — arXiv:2610.10955

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10955
License (as archived)
CC0-1.0
Archived
2026-10-09T06:29:55.958Z
SHA-256 of the archived text
d0c73bc2e7f05769a600658a43deca19501a5ed2df91d2c119b04e0232d020da
Stable URL of this page
https://metraipolis.com/documento/dc_519b58efcec8

How to cite

Learning Multi-Step Query Rewriting via Corpus Feedback for Conversational Search — arXiv:2610.10955 — arXiv (en), https://arxiv.org/abs/2610.10955 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_519b58efcec8 (Metraipolis archive dc_519b58efcec8, sha256 d0c73bc2e7f05769a600658a43deca19501a5ed2df91d2c119b04e0232d020da)
BibTeX
@misc{dc519b58efcec8,
  title = {Learning Multi-Step Query Rewriting via Corpus Feedback for Conversational Search — arXiv:2610.10955},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10955},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_519b58efcec8; sha256 d0c73bc2e7f05769a600658a43deca19501a5ed2df91d2c119b04e0232d020da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10955. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conversational Query Rewriting (CQR) turns a context dependent user turn into a standalone query for a retriever, and most methods do this in a single step from the dialogue history before retrieving once. The rewrite is therefore fixed before any corpus evidence is available to correct its reference resolution or its vocabulary. We recast CQR as a sequential retrieval problem: an agent rewrites the current turn, retrieves, and conditions its next rewrite on the returned passages. The agent acts in a typed space of three rewriting operations, resolving conversational intent into a standalone query, generating lexical reformulations, or synthesizing pseudo-documents for document-to-document matching, together with a stop action that ends the episode. We train the policy with supervised fine-tuning followed by reinforcement learning against a single retrieval-quality reward, using no human rewrite annotations. Across TopiOCQA and QReCC, the agent outperforms several retrieval-aligned baselines, while remaining effective across retrieval backends and generalizing to the CAsT benchmarks without additional training. Further analysis shows that, through retrieval-reward optimization alone, the learned policy develops a behavior of grounding pseudo-documents in passages retrieved by earlier steps, substantially improving retrieval.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.10955 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:54:51.494Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).