arXiv Computation and Language

Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers

arXiv Computation and Language
4d ago

Parameter-Efficient Retrievers for Polish and European Languages

The paper introduces a three‑stage training pipeline that builds compact, efficient dense retrievers without requiring ground‑truth relevance labels. Using cross‑lingual alignment, relational knowledge distillation, and contrastive fine‑tuning, the authors develop PolDense (six Polish models ranging from 17 M to 1 B parameters) and EuroDense (a 435 M‑parameter model covering nine European languages). Extensive evaluation on 41 Polish and 150 multilingual tasks shows that PolDense‑1B outperforms larger retrievers up to 9 B parameters, while EuroDense leads in task‑averaged and language‑averaged performance among models below 1 B parameters.

By S{\l}awomir Dadas, Rafa{\l} Po\'swiata, Ma{\l}gorzata Gr\k{e}bowiec, Micha{\l} Pere{\l}kiewicz
arXiv AI
Aug 19

DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval

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.

By Jingyuan Wang, Richong Zhang, Zhijie Nie, Mingxin Li, Yanzhao Zhang
arXiv AI
Sep 4

STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation

The paper introduces STAIR, a retrieval system that uses a document’s Table of Contents to guide large language models in accessing global structure, thereby reducing hallucinations in Retrieval Augmented Generation. Experiments with a fine‑tuned Differentiable Search Index show that ToC‑based retrieval yields a low hallucination rate (<0.05%) and improves Recall@1 to 82.6% on the newly released SearchTome benchmark, outperforming baselines like BM25, DPR, and Mistral. The authors also release SearchTome, a diverse dataset of 18 books across six domains, to encourage further research in ToC‑based retrieval.

By Vineet Kumar, Meghanadh Pulivarthi, vishwajeet kumar, Jaydeep Sen, Riyaz Ahmad Bhat, Sachindra Joshi
Hugging Face Trending Papers
Jul 21

RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency

Public institutions hold large volumes of sensitive documents and support tickets that cannot leave the premises, ruling out cloud-hosted language models entirely. We report on RAGAL, a retrieval-augmented assistant for the technical-support team of AFIR, the Romanian Agency for Financing Rural Investments, built and operated under three hard constraints: zero data egress (no external API calls, even for synthetic data), a read-only mandate (the assistant drafts, humans execute), and a single 8 GB consumer laptop as the only development and training machine.

arXiv Computation and Language
Aug 31

Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection

The paper investigates modular entity disambiguation by separating candidate retrieval from entity selection. It compares sparse retrieval (BM25), Web KB search, and a dense retriever, all paired with large language model selectors. Results show that a training‑free BM25 retriever combined with an LLM selector achieves state‑of‑the‑art performance on the ZELDA benchmark, and the modular approach enables abstention when retrieval fails.

By Fina Polat, Daniel Daza, Pengyu Zhang, Klim Zaporojets, Paul Groth
arXiv Machine Learning
Jun 30

Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation

arXiv:2606. 29947v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regimes.

By Zhe Dong (University of Maine at Presque Isle), Fang Qin (Stanford University), Manish Shah (Independent Researcher), Yicheng Wang (Independent Researcher)
arXiv AI
Jun 6

QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving

arXiv:2606. 05875v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost.

By Jianxin Yan, Wangze Ni, Zhenxin Li, Jiabao Jin, Zhitao Shen, Haoyang Li, Jia Zhu, Peng Cheng, Xuemin Lin, Lei Chen, Kui Ren
arXiv AI
Aug 25

Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling

The paper introduces LLM-QL, a dense retrieval model that harnesses large language models (LLMs) by maximizing query likelihood (QL) as an auxiliary task. It incorporates an Attention Block to limit predictive token attention to document tokens before the ending token and a Document Corruption component that masks parts of the document during prediction. Experiments on MS MARCO and BEIR datasets show that LLM-QL outperforms other LLM-based retrievers, and detailed analyses confirm the effectiveness of its components.

By Hengran Zhang, Keping Bi, Jiafeng Guo, Xiaojie Sun, Shihao Liu, Daiting Shi, Dawei Yin, Xueqi Cheng
Hugging Face Trending Papers
Jun 4

QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving

Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost. RAG cache fusion reduces this cost by reusing precomputed key-value (KV) caches for retrieved chunks and selectively recomputing tokens under the current prompt.

arXiv AI
Sep 1

Look It Up: Analysing Internal Web Search Capabilities of Modern LLMs

The paper evaluates how modern large language models use internal web search to answer factual questions. Using 783 static queries and 288 dynamic queries, the authors find that enabling retrieval improves accuracy on static questions but hurts confidence calibration. On dynamic queries, models often retrieve but still achieve less than 70% accuracy, mainly due to poor query formulation and source selection, indicating that internal web search works better as a quick verification tool than a full information‑retrieval system.

By Sahil Kale