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: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...
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.
arXiv:2604. 23336v3 Announce Type: replace-cross Abstract: Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs.
E2Rank (Efficient Embedding-based Ranking) is a unified framework that extends a single text embedding model to perform both retrieval and listwise reranking. By treating the listwise prompt—constructed from the query and its top‑K candidates—as a pseudo‑relevance feedback query, E2Rank reranks via cosine similarity against precomputed document embeddings, avoiding costly autoregressive decoding. The approach achieves state‑of‑the‑art results on BEIR, competitive performance on the reasoning‑intensive BRIGHT benchmark, lower latency than existing LLM‑based rerankers, and improved embedding performance on MTEB—all within a single model.
arXiv:2604.05087v4 Announce Type: replace Abstract: Generative large language models (LLMs) are increasingly used as inference-time components in retrieval pipelines, for tasks such as query rewritin...
The paper introduces DEPT, a method that trains a single decoder-only large language model to both expand queries and encode documents for retrieval. By preserving document embeddings close to their initial cached values while allowing gradients to flow through the generator, DEPT stabilizes retrieval targets and enables efficient index reuse and online hard‑negative mining. Experiments on the BEIR benchmark with Qwen3‑4B‑Instruct‑2507 and LLaMA‑3.2‑3B‑Instruct show that DEPT outperforms training‑free, independently trained, and staged unified baselines, with ablations confirming the benefits of preservation, whitening, end‑to‑end expansion training, and online negatives.
arXiv:2606. 04194v1 Announce Type: new Abstract: Retrieving the few past turns that answer a new query across long multi-session histories is the retrieval bottleneck behind long-term conversational memory (LoCoMo, LongMemEval).
arXiv:2607. 11933v1 Announce Type: cross Abstract: Cross-encoders achieve high reranking accuracy in Retrieval-Augmented Generation (RAG) pipelines but impose quadratic inference costs that limit real-time deployment.
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:2606. 28367v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval.
The paper presents a controlled comparison of six retrieval-augmented generation (RAG) strategies for scientific question answering on a large arXiv corpus. All pipelines use the same LLM generator and evaluation protocol, differing only in retrieval design—ranging from classic dense retrieval to late‑interaction methods like ColBERTv2. The authors also release a synthetic question dataset and code to enable reproducible, large‑scale evaluation of RAG trade‑offs.
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.