Glance is a retrieval‑augmented generation approach that eliminates the need for separate reranker models by adding a lightweight decision adapter and pointer head to a single 9B backbone. It scores candidate passages directly from a shared prefill, requiring only about 0.1 GiB of extra memory per decision skill. In fine‑tuning on MS MARCO, Glance outperforms the bge‑reranker‑v2‑m3 on SciFact and NFCorpus, and improves answer F1 on HotpotQA by 0.045, while scaling to 200 candidates it surpasses cross‑encoder reranking by 0.058 nDCG@10.
arXiv:2608. 14841v1 Announce Type: new Abstract: Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines.
arXiv:2605. 04495v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on evidence ranking to determine what information is exposed to the generator, yet existing retrieval and reranking methods primarily estimate query--document relevance.
Lychee‑Reranker is a fast, not‑late‑interaction reranker that decouples query and passage computation while preserving expressive relevance modeling. It uses an encoder–decoder architecture: passages are pre‑encoded with Matryoshka embedding pooling, and the decoder jointly processes system/user instructions and query intent, with cross‑attention capturing fine‑grained relevance. The design yields four benefits—offline passage encoding for efficiency, cross‑attention expressiveness, compact Matryoshka pooling, and adjustable test‑time compute—and is available in Nano, Small, and Large sizes (0.27B, 1B, and 4B activated parameters).
arXiv:2607. 27692v1 Announce Type: cross Abstract: Top-$K$ sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries.
As retrieval systems scale, high-quality reranking becomes increasingly important. However, most existing rerankers, whether encoder-based or decoder-based, jointly encode the query and passage, tightly coupling their computation and limiting deployment efficiency as well as flexibility.
DualView is an efficient dual‑view cascaded reranking framework designed for multi‑hop document reranking in question answering. It combines a Local Scorer that uses stacked cross‑attention for fine‑grained query‑document relevance with a Global Scorer that models inter‑document dependencies via Transformer‑based context aggregation. An Adaptive Gate dynamically fuses these views based on query semantics, achieving high recall and low latency on benchmarks such as MuSiQue.
Re$^3$Rank is a listwise reranker that uses reasoning-conditioned retrieval heads (RRHeads). It generates a reasoning trace for each candidate, then scores candidates by using the trace tokens as attention queries for selected RRHeads, producing continuous relevance scores. A straight‑through estimator allows joint training of the generator and scorer, and on nine benchmarks the 4B model outperforms 11 baseline rerankers by an average of 3.11 NDCG@10 points, while the 0.6B model beats rerankers with up to 32B parameters.
Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost. We study when this actually helps, using GCCP/PAGC as a representative method.
arXiv:2606.22807v3 Announce Type: replace Abstract: As retrieval systems scale, effective and efficient reranking becomes increasingly important. However, most existing encoder- and decoder-based rer...
arXiv:2608. 10528v1 Announce Type: cross Abstract: Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost.
The paper investigates whether System‑1‑style decision models can replace dedicated rerankers in retrieval‑augmented generation (RAG) systems. After screening 21 open‑weight models on 11 benchmarks, the authors compare a promising decision model with a dedicated reranker on identical candidate lists. While limiting candidate text length improves reliability and makes some configurations competitive, a tuned reranker remains faster and uses less GPU memory, indicating that replacing a reranker requires balancing quality, latency, and memory.
arXiv:2608. 03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19.