arXiv:2605. 02950v2 Announce Type: replace-cross Abstract: Transformer-based semantic encoders are effective for retrieval, but in many deployments the recurring bottleneck is online query encoding rather than offline corpus indexing.
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.
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:2608. 02112v1 Announce Type: new Abstract: Embedding benchmarks measure standalone model quality, but they do not establish whether a low-cost retriever contributes complementary ranking information once lexical and transformer-based retrieval are already combined.
Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models (118M to 14B parameters) on 37 tasks spanning classification, semantic textual similarity (STS), clustering, pair classification, and retrieval.
arXiv:2605. 11374v5 Announce Type: replace Abstract: Test-time compute is widely believed to benefit only large reasoning models, leaving small models with nothing to gain.
Retrieval in the SQL setting has largely been studied as the task of finding, within a large collection of SQL statements, the statement that answers a natural-language question. At scale, however, a more fundamental retrieval problem precedes generation: schema retrieval, identifying the tables and columns a question requires in a database that may contain thousands of them, far more than fit in a model's context.
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 investigates the geometric capacity of vector retrieval systems, focusing on the maximum recall achievable with a fixed document index. It demonstrates that, on real-world benchmarks, single-vector query encoders often underperform relative to the index’s potential. The authors provide theoretical evidence that learning such encoders can be computationally hard, constructing a task where a simple neural network can achieve perfect recall while any statistical-query learner would need exponentially many queries to surpass random chance.
arXiv:2610.07731v1 Announce Type: cross Abstract: Dense retrieval models are typically trained with contrastive objectives that learn effective representations but do not directly optimize retrieval...
arXiv:2607. 04071v1 Announce Type: cross Abstract: Portuguese remains underrepresented in text embedding evaluation, despite being one of the most widely spoken languages in the world.
arXiv:2609.23307v1 Announce Type: cross Abstract: This paper presents a comparative evaluation of dense embedding models for semantic candidate-job matching in high-volume staffing workflows. Incomin...
CORE improves compositional reasoning in multimodal language models by distilling a cross‑attentive reranker’s fine‑grained judgments into the embedding model. It generates candidate lists across five compositional matching levels and trains with a Rank‑KL objective to replicate the reranker’s ranking. Experiments on COLA, SUGARCREPE++, and NEGBENCH show CORE‑RERANKER‑8B outperforms Jina‑Reranker by 10.7 points, while CORE‑EMBED‑8B achieves the best overall average among evaluated embeddings, with gains also transferring to the MCMR benchmark without harming COCO or Flickr30K retrieval.