https://ym-xu.github.io/living-survey/fields/rag/#tag=evalBenchmarks, hallucination, attribution and faithfulness to the retrieved context.Thu, 12 Nov 2026 15:12:01 +0000https://arxiv.org/abs/2611.14263https://arxiv.org/abs/2611.14263Tue, 10 Nov 2026 00:00:00 +0000Wenqi Zhou, Leonardo Baldo, Kai Goebel, Manuel Arias Chao Fault diagnosis in complex systems requires linking observed changes in physical quantities to the failure mechanisms that produce them. Experienced engineers perform this task by combining sensor information with knowledge of system behavior and fault propagation. Large Language Models (LLMs) can support this process,…https://arxiv.org/abs/2611.11960https://arxiv.org/abs/2611.11960Mon, 09 Nov 2026 00:00:00 +0000Guoqing Zhang, Rafik Hadfi, Takayuki Ito Unplanned 30-day intensive care unit (ICU) readmission is a critical benchmark for evaluating healthcare quality. Most predictive models assume readmission risk depends solely on a patient's individual pathophysiological state, ignoring hospital operational context and resource capacity. In practice, discharge decision…https://arxiv.org/abs/2611.09807https://arxiv.org/abs/2611.09807Fri, 06 Nov 2026 00:00:00 +0000Osamudiamen Edogun, Joshua Obigwe, Irfan Mehmood A conversational agent that remembers has to decide what to keep. Retrieval-augmented generation keeps the transcript and searches it; the alternative is to compact each turn into atomic facts and search those. We compare the two on LoCoMo, with both arms answering all 1,985 questions in one window, against the same st…https://arxiv.org/abs/2611.09791https://arxiv.org/abs/2611.09791Fri, 06 Nov 2026 00:00:00 +0000Gabriel Souza Baggio, Gabriel Machado Lunardi, Guilherme Medeiros Machado, Subhankar Maity, et al. Competitive programming problems pose distinctive challenges for Large Language Models, as they demand not only proficient code generation but also advanced algorithmic reasoning. This study presents a Retrieval-Augmented Generation approach specifically designed to enhance the capacity of Large Language Models to addr…https://arxiv.org/abs/2611.09423https://arxiv.org/abs/2611.09423Fri, 06 Nov 2026 00:00:00 +0000Sofia Campos, Carlos Martins, Pedro Pires, João Gama, et al. In the healthcare sector, claim denials impose significant financial and administrative burdens, emphasizing the need for automated and trustworthy decision-support systems. This paper proposes a modular Agentic Artificial Intelligence (AI) framework for healthcare claim denial analysis, integrating specialized agents …https://arxiv.org/abs/2611.06715https://arxiv.org/abs/2611.06715Wed, 04 Nov 2026 00:00:00 +0000Zohreh Abbasi Liasi, Batoul Hammoud, Anas Madkoor, Ehsaneddin Asgari Retrieval-augmented generation (RAG) assumes that language models can reason over relations stated in their context rather than fall back on associations memorized during pretraining. We study this evidence-conditioned relational reasoning in isolation, with the facts supplied directly in the prompt rather than retriev…https://arxiv.org/abs/2611.03747https://arxiv.org/abs/2611.03747Mon, 02 Nov 2026 00:00:00 +0000Huan Phong Thai, Thu Anh Ngoc Le, Nhu Huynh Thi Le, Nhan Huu Tran, et al. Natural Language Processing (NLP) has been widely applied in financial domains, enabling automated analysis and retrieval of stock market information. However, traditional NLP-based systems often struggle with maintaining contextual accuracy and generating relevant responses in dynamic financial environments. To addres…https://arxiv.org/abs/2611.02810https://arxiv.org/abs/2611.02810Mon, 02 Nov 2026 00:00:00 +0000Yingtao Ren, Xiao Luo, Yiwei Fu, Jinzhao Zhou, et al. · EMNLP 2026 This paper studies retrieval-augmented generation (RAG), which leverages external knowledge to improve the performance of language models. Despite the remarkable progress, current RAG approaches are still far from satisfactory due to inadequate retrieval and potential hallucinations. Towards this end, we propose a nove…https://arxiv.org/abs/2611.03725https://arxiv.org/abs/2611.03725Sun, 01 Nov 2026 00:00:00 +0000Hira Naveed, Scott Barnett, Stefanus Kurniawan, John Grundy, et al. Retrieval-Augmented Generation (RAG) pipelines are widely used for domain-specific question answering, yet locating faults remains manual and time-consuming. Fault localization is challenging because RAG pipelines consist of interdependent stages, where faults can propagate downstream, masking their origin, or remain u…https://arxiv.org/abs/2611.01910https://arxiv.org/abs/2611.01910Sun, 01 Nov 2026 00:00:00 +0000Sonam Gupta, Vignesh P, Vishwajeet Kumar, Adnan Qidwai, et al. Retrieval-Augmented Generation (RAG) for multi-hop reasoning requires retrieval to adapt as intermediate evidence reveals new information needs. Existing approaches support such retrieval through explicit graph structures or iterative query reformulation, introducing graph-construction or query-time overhead. We presen…https://arxiv.org/abs/2611.01409https://arxiv.org/abs/2611.01409Sun, 01 Nov 2026 00:00:00 +0000Elyas Irankhah, Shahed Salehzehi, Parisa Hosseini Purpose: Retrieval-augmented generation (RAG) can introduce electrocardiogram (ECG) criteria that lack patient-specific measurement support. This study evaluates the reliability of retrieved diagnostic criteria in AI-generated ECG reports. Methods: We analyzed 1,083 human-validated PTB-XL patient records using a librar…https://arxiv.org/abs/2611.00871https://arxiv.org/abs/2611.00871Sat, 31 Oct 2026 00:00:00 +0000Youmin Ko, Jihong Jeong, Hyunjoon Kim · NeurIPS 2026 Despite advances in retrieval-augmented generation (RAG), suppressing hallucinations during complex reasoning remains a persistent challenge. We identify that existing RAG pipelines suffer from a textual bottleneck: by passing only raw text to the generator, they discard discriminative signals of the retriever. Further…https://arxiv.org/abs/2611.00344https://arxiv.org/abs/2611.00344Fri, 30 Oct 2026 00:00:00 +0000Dmytro Kurdydyk, Aadi Palnitkar, Sebastian Scherer, Seungchan Kim Retrieval-augmented generation (RAG) systems have seen growing adoption in embodied settings as language-queryable memories of the environment. However, existing approaches often assume a reliable single-episode knowledge base (KB) or accumulate observations across episodes without correcting prior errors. Such errors …https://arxiv.org/abs/2610.40966https://arxiv.org/abs/2610.40966Thu, 29 Oct 2026 00:00:00 +0000Ivan Kochergin, Vasily Konovalov Conversational RAG benchmarks such as MTRAG and RETECO evaluate retrieval and generation end to end: each system answers from its own retrieval, so abstention must be scored against whether each retrieved context is sufficient. A convenient shortcut reads sufficiency off the relevance judgments and treats a context wit…https://arxiv.org/abs/2610.40742https://arxiv.org/abs/2610.40742Thu, 29 Oct 2026 00:00:00 +0000Chahana Dahal, Zuobin Xiong Retrieval-Augmented Generation (RAG) is vulnerable to knowledge poisoning, where adversaries manipulate retrieved evidence to influence model outputs. Existing defenses are primarily evaluated using attack success rate (ASR), which obscures defense-induced failures and the mechanisms behind apparent attack prevention. …https://arxiv.org/abs/2610.39231https://arxiv.org/abs/2610.39231Thu, 29 Oct 2026 00:00:00 +0000Siqing Huo, Andrew Parry, Debasis Ganguly, Mark Smucker, et al. Recent systems applying retrieval-augmented generation (RAG) and "deep research" iteratively generate queries, retrieve documents, and examine their contents, using the resulting information to guide subsequent search steps. When this process is carried out autonomously rather than by a human searcher, the system must …https://arxiv.org/abs/2610.37962https://arxiv.org/abs/2610.37962Tue, 27 Oct 2026 00:00:00 +0000Carlos Peláez-González, Francisco Herrera, Andrés Herrera-Poyatos Large Language Models (LLMs) are increasingly used as recommendation generators in conversational recommender systems (RS) via retrieval-augmented generation (RAG). This flexible design introduces new sources of structural bias. This paper studies positional bias in top-1 and single-turn LLM-based RS: systematic depend…https://arxiv.org/abs/2610.37728https://arxiv.org/abs/2610.37728Tue, 27 Oct 2026 00:00:00 +0000Fakabbir Amin A key challenge of RAG systems is retrieving information from enterprise documents created by multiple teams over time, where it is not possible to enrich the information using the latest information and metadata available outside the scope of organizational documentation responsibility. We investigated whether using a…https://arxiv.org/abs/2610.37358https://arxiv.org/abs/2610.37358Tue, 27 Oct 2026 00:00:00 +0000Zhouting Zhao Retrieval-augmented generation (RAG) can benefit from more sophisticated retrieval, but extra retrieval may be unnecessary for many questions and gains in evidence retrieval may not translate into faithful or correct answers. We study a cost-aware, two-action retrieval policy that chooses between a dense-retrieval-plus…https://arxiv.org/abs/2610.37237https://arxiv.org/abs/2610.37237Tue, 27 Oct 2026 00:00:00 +0000Wadie El Amrani, Luis Galárraga GraphRAG systems often use knowledge graphs to retrieve relevant context for an LLM that produces the final answer. That makes answers more inscrutable and therefore less appealing for domains where transparency is paramount. We present GraphRAGProv, an architecture that executes SPARQL queries over source-grounded RDF…https://arxiv.org/abs/2610.36915https://arxiv.org/abs/2610.36915Tue, 27 Oct 2026 00:00:00 +0000Parv Khatri, Harshul Jain, Mehak Kapoor, Tanya Sah When the sources retrieved for a query disagree, the right response depends on why they disagree: a question with several valid answers, a contested topic, stale information and a false source each call for different behaviour. Cattan et al. (2025) showed that telling a generator the conflict type improves its response…https://arxiv.org/abs/2610.36650https://arxiv.org/abs/2610.36650Tue, 27 Oct 2026 00:00:00 +0000Amiri Hayes, Kristina Wicke Graph-structured representations of text data have become foundational across machine learning, yet it remains unclear how to systematically construct a graph from a given dataset for a target task. Choices about which entities become nodes, which relationships become edges, and what text each node contains can substan…https://arxiv.org/abs/2610.36561https://arxiv.org/abs/2610.36561Tue, 27 Oct 2026 00:00:00 +0000Andres Cruz Degante Deploying conversational assistants at government service desks faces a tension between regulatory certainty (zero tolerance for invented fees), data sovereignty prohibiting commercial clouds, and high rates of underspecified or out-of-jurisdiction citizen queries. We present and evaluate a governed, sovereign Retrieva…https://arxiv.org/abs/2610.36444https://arxiv.org/abs/2610.36444Tue, 27 Oct 2026 00:00:00 +0000Zekai Chen, Hao Zhu, Yu Liu, Xunkai Li, et al. Web-based applications increasingly rely on understanding long multimodal documents, where answering questions often requires combining information across pages, tables, and figures. Agentic retrieval-augmented generation addresses these tasks through iterative retrieval and reasoning. However, Agentic execution is not…https://arxiv.org/abs/2610.36433https://arxiv.org/abs/2610.36433Tue, 27 Oct 2026 00:00:00 +0000Xianxiang Zhao, Advik Mehta, Falak Sethi, Brian Gue, et al. Construction safety management still struggles to produce daily safety bulletins (DSBs), structured daily communications that identify site-specific hazards, convey safety protocols, and set preventive measures for workers. Manual DSB creation takes 2-3 hours daily and yields inconsistent quality, with 25% of crews nev…https://arxiv.org/abs/2610.36335https://arxiv.org/abs/2610.36335Mon, 26 Oct 2026 00:00:00 +0000Hui Yang, Jiaoyan Chen, Yongsheng Gao Large language models (LLMs) perform well across many real-world tasks but remain prone to hallucination, limiting their reliability in domains such as biomedicine and healthcare, where answers must be grounded in established knowledge. Retrieval-augmented generation (RAG) mitigates this problem by incorporating extern…https://arxiv.org/abs/2610.35635https://arxiv.org/abs/2610.35635Mon, 26 Oct 2026 00:00:00 +0000Joao P. A. Dantas · NeurIPS 2025 Workshop An offline language-based support tool is presented to assist pilot training and tactical decision-making in air combat operations. The system, named MATE (Mission Assistant for Training and Evaluation), applies retrieval-augmented generation (RAG) to answer natural language questions using content extracted from doctr…https://arxiv.org/abs/2610.35142https://arxiv.org/abs/2610.35142Mon, 26 Oct 2026 00:00:00 +0000Qianchi Zhang, Hainan Zhang, Liang Pang, Hongwei Zheng, et al. Large language models (LLMs) often produce plausible but incorrect answers, motivating reinforcement learning methods that reward correct answers, penalize incorrect answers, and allow abstention. However, fixed outcome-based rewards do not distinguish incorrect responses with different confidence levels or account for…https://arxiv.org/abs/2610.35094https://arxiv.org/abs/2610.35094Mon, 26 Oct 2026 00:00:00 +0000Ivana Crescenzi, Arianna Muti, Maarten Sap, Tommaso Caselli, et al. Implicit misogyny often requires background knowledge to be understood. To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework for detecting and explaining implicit misogyny in English and Italian, leveraging encyclopedic, slang and feminist knowledge sources. Using the ImplicIT-Mis and …https://arxiv.org/abs/2610.35056https://arxiv.org/abs/2610.35056Mon, 26 Oct 2026 00:00:00 +0000Runsong Jia, Qian Chang, Mengjia Wu, Ciprian Doru Giurcăneanu, et al. · EMNLP 2026 Findings Retrieval-augmented generation (RAG) grounds language models in retrieved evidence, but its outputs often contain claims unsupported by that evidence. Recent multi-agent RAG systems decompose the pipeline into cooperative decisions, yet they typically optimize all agents under a shared task reward such as EM or F1, whi…https://arxiv.org/abs/2610.34872https://arxiv.org/abs/2610.34872Mon, 26 Oct 2026 00:00:00 +0000Muhammad Aimal Rehman, Chi-Kuang Yeh Retrieval-augmented generation (RAG) can improve factual grounding without guaranteeing that every generated claim is supported. Previous work has studied claim-level conformal factuality in single-stage RAG and, more recently, multi-hop RAG. We examine its behavior in agentic RAG, where a language-model policy adaptiv…https://arxiv.org/abs/2610.34829https://arxiv.org/abs/2610.34829Mon, 26 Oct 2026 00:00:00 +0000Hangyi Zhao, Bonan Zhang, Fusen Guo, Jiaheng Wei, et al. Single-document corpus poisoning under black-box access poses a severe threat to Retrieval-Augmented Generation (RAG). However, existing attacks predominantly rely on explicit factual refutations or imperative instruction overrides. Modern aligned LLMs often arbitrate such conflicts conservatively, rejecting overt cont…https://arxiv.org/abs/2610.34816https://arxiv.org/abs/2610.34816Mon, 26 Oct 2026 00:00:00 +0000Qiaomu Li, Ying Xie Retrieval-augmented generation (RAG) systems often use a dedicated reranker to choose which retrieved candidates reach the language model. Reranking improves relevance but adds latency, so teams look for faster alternatives. System-1style decision models make direct, structured predictions instead of generating long re…https://arxiv.org/abs/2610.34585https://arxiv.org/abs/2610.34585Sun, 25 Oct 2026 00:00:00 +0000Bahaeddin Türkoğlu Large language models (LLMs) are neural networks trained on huge text collections to generate text by predicting what comes next. Engineers using ChatGPT and other generative artificial intelligence (AI) tools need a clear picture of what training changes and prompts add. The article starts with the Transformer, which …https://arxiv.org/abs/2610.34391https://arxiv.org/abs/2610.34391Sun, 25 Oct 2026 00:00:00 +0000Ivan Iorsh, Aleksandr Kapitonov, Ivan Filianin, Matvey Lesonen, et al. Scientific literature in materials physics is growing faster than researchers can manually inspect it, yet most retrieval tools rely on keyword matching or generic question answering that ignores domain-specific structure in PDF files. This paper presents an end-to-end pipeline that transforms arXiv superconductivity p…https://arxiv.org/abs/2610.37697https://arxiv.org/abs/2610.37697Sat, 24 Oct 2026 00:00:00 +0000Joe Egan, Ben Elliot, Samuel Van Stroud, Alex Sopio, et al. Large scientific collaborations produce extensive internal documentation spread across heterogeneous systems, making it difficult for collaborators to locate and reuse existing knowledge. We present chATLAS, a deployed Retrieval-Augmented Generation (RAG) assistant developed for the ATLAS experiment at CERN. The system…https://arxiv.org/abs/2610.33849https://arxiv.org/abs/2610.33849Sat, 24 Oct 2026 00:00:00 +0000Pushkal Kumar, Arvin Sahaym Query-time filters that screen each retrieved document before it reaches the generator are the dominant published defense against retrieval-augmented generation poisoning, and they report near-perfect detection on domain benchmarks. We show that this performance is predicted by how the poison set was built rather than …https://arxiv.org/abs/2610.32435https://arxiv.org/abs/2610.32435Fri, 23 Oct 2026 00:00:00 +0000Juan Li, Fangshu Chang, Xinyi Jiang, Ling Huang, et al. Building Task-Oriented Dialogue (TOD) systems for high-value scenarios such as financial marketing requires large volumes of domain-specific dialogue data, which privacy regulations, annotation costs, and the need for expert labor make hard to obtain. User simulation offers a remedy, but existing methods target general…https://arxiv.org/abs/2610.31606https://arxiv.org/abs/2610.31606Thu, 22 Oct 2026 00:00:00 +0000Miguel Mochizuki Silva, Samuel Ismael, Mateus C. Dias, Thaís Gaudêncio, et al. Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage. Methods: An 18-document corpus and an 18-query development benchmark, with one Y…https://arxiv.org/abs/2610.31467https://arxiv.org/abs/2610.31467Thu, 22 Oct 2026 00:00:00 +0000Bayram Ayadi, Florian Geissler, Johanna Schmidhuber As wearable and digital health systems increasingly generate longitudinal physiological records, communicating these observations in patient-accessible language remains a significant challenge. Large Language Models (LLMs) offer a promising mechanism for translating structured clinical information into readable narrati…