| title | Glance: The Generator Is Its Own Reranker |
|---|---|
| authors | Adilet Metinov, Chingiz Arziev |
| date | 2026-10-29 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.40454 |
| affiliation | Airun Intelligence Labs |
| upvotes | 11 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| 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. |
cite
@misc{metinov2026glance,
title={Glance: The Generator Is Its Own Reranker},
author={Adilet Metinov and Chingiz Arziev},
year={2026},
eprint={2610.40454},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.40454}
}