Metraipolis › archive › dc_3fe2cac32b32

Seek: Self-Evaluative Exploration for Knowledge Retrieval — arXiv:2609.28980

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28980
License (as archived)
CC0-1.0
Archived
2026-10-08T06:43:55.084Z
SHA-256 of the archived text
fa0066002b89bfffcbb9592abc185c8b706ddbf58e5d1a5567cff2b7cb907bf4
Stable URL of this page
https://metraipolis.com/documento/dc_3fe2cac32b32

How to cite

Seek: Self-Evaluative Exploration for Knowledge Retrieval — arXiv:2609.28980 — arXiv (en), https://arxiv.org/abs/2609.28980 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fe2cac32b32 (Metraipolis archive dc_3fe2cac32b32, sha256 fa0066002b89bfffcbb9592abc185c8b706ddbf58e5d1a5567cff2b7cb907bf4)
BibTeX
@misc{dc3fe2cac32b32,
  title = {Seek: Self-Evaluative Exploration for Knowledge Retrieval — arXiv:2609.28980},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28980},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fe2cac32b32; sha256 fa0066002b89bfffcbb9592abc185c8b706ddbf58e5d1a5567cff2b7cb907bf4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28980. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based retrievers and rerankers have advanced passage ranking, yet both paradigms interact with the corpus in a single pass and commit to the resulting candidate set, leaving relevant documents permanently unrecoverable once missed. We introduce Seek, Self-Evaluative Exploration for Knowledge Retrieval, a training-free framework that addresses this limitation through iterative corpus interaction at test time. At each round, an LLM generates pseudo-passages conditioned on accumulated relevance feedback, a retriever surfaces fresh candidates, and a dedicated assessor assigns graded relevance judgments that guide subsequent rounds. On TREC Deep Learning, Seek matches trained rerankers in ranking quality while consistently improving Recall@100 over single-pass BM25. On the reasoning-intensive BRIGHT benchmark, Seek with Qwen2.5-7B achieves an 82% relative gain over BM25, surpassing all trained baselines, and Seek with GPT-4.1 reaches 37.4 average nDCG@10, exceeding the strongest baseline by 37%.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.28980 — 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 2026-10-08T06:09:07.173Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).