Metraipolis › archive › dc_255ce2fc9fa8

GistRank: Gist-Compressed Listwise Ranking with Large Language Models — arXiv:2610.39610

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39610
License (as archived): CC0-1.0
Archived: 2026-11-01T02:39:59.838Z
SHA-256 of the archived text: 0c9cff36fbd9eeac4305db80f300cbe9f5e62daa7a14c8f5e2f11a801ea19f70
Stable URL of this page: https://metraipolis.com/documento/dc_255ce2fc9fa8

How to cite

GistRank: Gist-Compressed Listwise Ranking with Large Language Models — arXiv:2610.39610 — arXiv (en), https://arxiv.org/abs/2610.39610 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_255ce2fc9fa8 (Metraipolis archive dc_255ce2fc9fa8, sha256 0c9cff36fbd9eeac4305db80f300cbe9f5e62daa7a14c8f5e2f11a801ea19f70)

BibTeX

@misc{dc255ce2fc9fa8,
  title = {GistRank: Gist-Compressed Listwise Ranking with Large Language Models — arXiv:2610.39610},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39610},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_255ce2fc9fa8; sha256 0c9cff36fbd9eeac4305db80f300cbe9f5e62daa7a14c8f5e2f11a801ea19f70},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39610. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have become a powerful tool for listwise relevance ranking, which can improve web search by comparing retrieved passages jointly. However, processing every candidate verbatim and generating a permutation autoregressively can make inference costly, every candidate must be serialized verbatim into the prompt and the input therefore grows linearly with both the number and the length of the passages. While sliding-window ranking handles context limits through repeated re-encoding of overlapping blocks, hard compression techniques sacrifice the fine-grained details required for accurate discriminative judgment. To better understand and mitigate this trade-off, we conduct a comprehensive study of soft compression for LLM-based listwise ranking. Our findings reveal that a vanilla gist representation is ill-suited to ranking for two reasons: strictly causal encoding weakens how thoroughly each gist token absorbs its passage, and the representation is never trained to expose the relative-preference structure that separates closely competing candidates. To this end, we propose GistRank, a three-stage training framework that equips a large language model with gist-compressed passage representations by learning faithful gist tokens under a semi-bidirectional attention scheme, instilling discriminative comparison through pairwise training, and adapting the model to the listwise objective. GistRank collapses each passage into only $K{=}4$ gist tokens, this gives 14$\times$ speedups over one-shot full-text ranking while reaching 59.17 average nDCG@10 over TREC DL19/20 and five BEIR subsets within 0.89 of the strongest full-context baseline. Overall, GistRank provides an effective means to enhance efficiency for searches in real-world environments.

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/2610.39610 — 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 2026-11-01T02:16:28.227Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).