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 l
Glance integrates reranking and generation into a single backbone using lightweight adapters and pointer heads to score passages from shared context, reducing memory overhead while improving retrieval and answer quality.
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,…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Glance: The Generator Is Its Own Reranker was first seen on Hugging Face · Daily papers on Oct 30, 2026. Since then it has appeared in 40 checks on 4 different days. Its best position was #19 of 30, reached on Oct 30, 17:28 UTC. It dropped off the list after Nov 2, 13:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 2, 13:28 UTC, after 4 days of trending.
#19 on Hugging Face · Daily papers, on Oct 30, 17:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Oct 30, 2026 and has been on the list on 4 days (40 checks) since.