Glance：让生成器自己当重排器，单一 9B 骨干兼顾生成与重排

View PDF HTML (experimental)

Abstract:Retrieval-augmented generation commonly serves separate models for reranking and answering, duplicating model residency and passage processing. We introduce Glance, which equips the generator with a lightweight decision adapter and pointer head to score candidate passages from a shared prefill. Short relevance probes branch from the cached context, producing one score per passage without separately prefilling each query-passage pair. A single resident 9B backbone supports generation, general decisions and reranking, with approximately 0.1 GiB of additional memory per decision skill. After 39 minutes of MS MARCO fine-tuning, Glance achieves nDCG@10 of 0.741 on SciFact and 0.345 on NFCorpus, compared with 0.721 and 0.326 for bge-reranker-v2-m3. On 300 HotpotQA questions, its selected context improves answer F1 by 0.045 over cross-encoder-selected context under the same base generator (paired bootstrap 95% CI [0.014, 0.076]). In a scaling study, reranking quality keeps rising up to 200 candidates (43k tokens) scored from one shared prefill, where it exceeds the cross-encoder by 0.058 nDCG@10, and a probe-only activated adapter lets generation continue from the original passage cache. These initial results demonstrate generator-based reranking with one resident backbone; evaluation currently covers two retrieval datasets, one QA dataset and one backbone family.

Comments:	12 pages, 2 figures, 6 tables. Adapters and code: this https URL
Subjects:	Computation and Language (cs.CL); Information Retrieval (cs.IR)
ACM classes:	H.3.3; I.2.7
Cite as:	arXiv:2610.40454 [cs.CL]
	(or arXiv:2610.40454v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.40454 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Adilet Metinov [view email]
[v1] Thu, 29 Oct 2026 17:01:22 UTC (16 KB)