← Back to all news

Retrieval-augmented generation

Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.

6,126 stories · RSS feed

arXiv Computation and Language
Oct 5

World Embedding Benchmark

The World Embedding Benchmark introduces 8,000 simulation-based video cases covering fluid, solid, dynamic, and optical physics, each paired with physical annotations. It supports three tasks—text‑video retrieval, physical‑property regression, and multiple‑choice classification—to assess how well video embeddings capture physical alignment versus quantitative information. Experiments show that while pre‑trained models perform poorly on retrieval and classification, lightweight probes can extract useful physical data, and physics‑specific contrastive training improves alignment but harms regression, highlighting a trade‑off. Retrieval‑augmented generation using these embeddings further enhances the physical fidelity of generated videos.

By Yiqi Liu, Ruifeng Yuan, Yang Wang, Long Li, Fengyu Cai, Hou Pong Chan, Jialin Yu, Hao Zhang, Chenghua Lin, Chenghao Xiao
ragdiffusionmultimodalbenchmarkssafety
More like this →
arXiv Computation and Language
Oct 5

BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions

BioMol-MQA is a new question‑answering dataset focused on polypharmacy that combines a multimodal knowledge graph—containing both text and molecular structure—with challenging questions designed to test large language models’ ability to retrieve and reason over this diverse information. The dataset highlights the limitations of current retrieval‑augmented generation systems, which typically handle only single‑modality text, by demonstrating that existing LLMs perform poorly unless provided with the necessary multimodal background data. This underscores the need for more robust RAG frameworks capable of integrating multiple data types for accurate responses.

By Saptarshi Sengupta, Shuhua Yang, Paul Kwong Yu, Fali Wang, Suhang Wang
llmsragnlpmultimodalbenchmarks
More like this →
arXiv AI
Oct 5

MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search

MRVQ (Matryoshka Residual Vector Quantization) is a single post‑hoc residual quantizer designed for frozen embeddings that can be truncated to support any combination of embedding dimension and code rate. By dropping residual stages or embedding coordinates, MRVQ provides a single resident artifact that serves all evaluated (dimension, rate) pairs, achieving the lowest memory usage among tested designs. Although it uses 17.8–22.0× less memory than three separately trained QINCo2 indices and 1.89–2.02× less than a lean shared‑model steelman, it trades off a small drop in nDCG@10 on FiQA compared to per‑rate QINCo2, yet still outperforms PQ, OPQ, and AdANNS‑OPQ at matched code size.

By Sean Culatana, Shang-En Huang, Kang Li
ragefficiency
More like this →
arXiv AI
Oct 5

How Causality Bridges the Semantic Gap

The paper introduces CausalBridge, a framework that uses causal structure to assign semantics to unnamed variables in numerical measurements. By discovering a causal graph from the data and solving for variable embeddings constrained by this graph, the method aligns variable meanings with a language model, outperforming association‑based approaches. Experiments on questionnaires and robotics scenarios show high accuracy even when most variable names are masked, enabling rapid and cost‑effective system naming.

By Shuhao Zhang, Xuran Zhou, Han Guo, Pengtao Xie, Yujia Zheng
llmsragroboticssafety
More like this →
arXiv AI
Oct 5

Counterfactual Evidence Audits Predict LLM-Agent Susceptibility to Ranked Context

The paper introduces a counterfactual evidence audit to assess how large language model agents respond to different sets of documents. By exposing agents to two mirrored sets of five documents and measuring changes in six downstream decisions, the authors predict how the agents will behave when presented with a full 45‑document context. Across multiple open‑weight model families and tasks, the five‑document audit accurately forecasts full‑context effects, reducing prediction error by 62% and correctly identifying the direction of most material effects.

By Rana Muhammad Usman
llmsragagents
More like this →
arXiv AI
Oct 5

Sentence-Level Context Sensitivity as a Training-Free Detector of Unsupported Content, Evaluated Against Trained Verifiers

The paper proposes a training‑free detector that uses sentence‑level context sensitivity to identify unsupported content in retrieval‑augmented generation (RAG) answers. By re‑scoring each sentence with full context, no context, and each chunk removed, the method flags the chunk whose removal most reduces a sentence’s likelihood as the likely source. Evaluated on RAGTruth, TofuEval, and RAGBench, the detector outperforms answer‑level faithfulness scores, achieving AUCs up to 0.745 and matching per‑chunk fact‑checkers while using only a fraction of the compute required by large‑language‑model judges.

By Mohamed Aly Bouke
llmsragnlpbenchmarks
More like this →
arXiv Computation and Language
Oct 5

StanceEval 2026: The Second Stance Detection Shared Task

StanceEval 2026 is the second edition of a shared task on stance detection in Arabic social media, where systems must classify a tweet’s stance toward a target as Favor, Against, or None. The event featured two tracks: Track 1 tests cross‑target transfer on thematically related topics (Women Driving vs. Women Empowerment), while Track 2 evaluates cross‑domain transfer to entirely unseen targets (E‑Cars and Trimester System). With 80 registered teams and 30 submissions, top systems achieved $F_{avg2}$ scores of 0.8994 (Track 1) and 0.9400 (Track 2), surpassing baseline performance and highlighting challenges such as target polarization and dialectal nuance.

By Rasha Albalawi, Nuha Albadi, Hamzah Luqman, Asma Yamani, Maram Kurdi, Saad Ezzini, Ahmed Ashraf, Maged Al-Shaibani, Nora Alturayeif
llmsragfine-tuning
More like this →
arXiv Machine Learning
Oct 5

Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens

The paper introduces Tokenization with States (TWS), a method that segments neural recordings into behaviorally meaningful states defined by task events and represents each state as a token based on population geometry, bypassing neuron- or session-specific embeddings. TWS successfully decodes movement from regime boundaries that carry no target information and transfers across species and recording modalities with only a linear probe. The approach demonstrates that tokens derived from shared population dynamics can generalize across sessions, outperforming per-neuron foundation models that fail to generalize.

By Sangyoon Bae, Jiook Cha
ragnlp
More like this →
arXiv AI
Oct 5

From Benchmarks to Production: A Text-to-SQL System for Complex Financial Data

The paper introduces FLINT, a domain‑specialized Text‑to‑SQL system designed for complex financial databases where data is stored as opaque integer keys. FLINT employs a lookup agent to resolve natural‑language concepts, uses embedding‑based retrieval of query templates from a compact expert‑authored bank, and prunes large schemas by traversing foreign‑key chains. Evaluated on 359 questions across two production financial schemas, FLINT outperforms state‑of‑the‑art baselines and is already deployed in a financial data retrieval service.

By Arijit Sehanobish, Bruno Gomes Coelho, Guillaume Michel, Sophia Zhi, Valerie Faucon-Morin, Kristen Howell
llmsragagentsbenchmarksdata-engineering
More like this →