RAG Citation Faithfulness

RAG: Retrieval-Augmented Generation

Latest papers

17 papers2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

MuninAI: A Self-Hosted Agentic Framework for Independent Research Groups
Oct 16, 2026Markus Fischer, Jens Meiler, Matthias ElgetiScientific QA Agentic RAG
Institute for Drug Discovery, Leipzig University Medical School, Leipzig, Germany · Institute for Medical Physics and Biophysics, Leipzig University Medical School, Leipzig, Germany · Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Dresden/Leipzig, Germany +3
Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit
Oct 13, 2026Hoang Pham, Duc Anh Vu, Duy Tung Doan +2RL for RAG RAG Citation Faithfulness
Nanyang Technological University · Viettel AI, Viettel Group · VinUniversity
Attributable Post-Rationalization in RAG Citations: A Controlled Reproduction and an RLVR Comparison
Sep 19, 2026Mehedi Khan, Md. Shariful Islam BhuyanRAG Citation Faithfulness Retrieval-Augmented Generation
Department of Computer Science and Engineering Bangladesh University of Engineering and Technology
CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering
Sep 14, 2026Sumit Barua, Guan Hong, Halil Dursunoglu +2Retrieval-Augmented Generation Citation Verification
Department of Computer Science, Western Michigan University, Kalamazoo, MI, 49008, USA.
The Attribution-Compression Frontier in Retrieval-Augmented Generation
Sep 13, 2026Deepanshu ModyRAG Citation Faithfulness Retrieval-Augmented Generation
Center for Data Science New York University
GADR: Gathering Architecture Decision Records from Meeting Transcriptions
Aug 18, 2026Lucas Daniel Costa da Silva, Kiev GamaRAG Citation Faithfulness Document Information Extraction
Universidade Federal de Pernambuco (UFPE) Recife, Brasil
When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation
Aug 17, 2026Haolin Jin, Pengyue Yang, Huaming ChenRAG Citation Faithfulness Retrieval-Augmented Generation
School of Electrical and Computer Engineering The University of Sydney Sydney, NSW, Australia
CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering
Jul 27, 2026Zhichao Yan, Shizhao Li, Jiapu Wang +5Retrieval-Augmented Generation Question Answering
Shanxi University, Taiyuan, China · Nanjing University of Science and Technology, Nanjing, China · Nanyang Technological University, Singapore +3
DS@GT ARC at LongEval: Citation Integrity and Factual Grounding in Scientific QA
Jul 15, 2026Brandon Michaels, Brendon JohnsonRetrieval-Augmented Generation Citation Verification
Georgia Institute of Technology, North Ave NW, Atlanta, GA 30332
On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage
Jul 14, 2026Vinay Kumar ChagantiContextual Faithfulness Citation Verification
Independent Researcher
5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control
Jun 27, 2026Thien-Qua-T-Nguyen, Chi Hoang, Nguyen Tran +3RAG Citation Faithfulness Retrieval-Augmented Generation
University of Information Technology, Ho Chi Minh City, Vietnam · 2Vietnam National University Ho Chi Minh City, Ho Chi Minh City, Vietnam
ProvenAI: Provenance-Native Traces of Evidence in Generated Answers
Jun 24, 2026Mohammad Faizan, Dalal AlharthiMulti-Hop QA Data Provenance
College of Information Science University of Arizona
How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
Jun 9, 2026Ian van Dort, Maria HeussRAG Citation Faithfulness Retrieval-Augmented Generation
University of Amsterdam
FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG
Jun 4, 2026Zhe Yu, Wenpeng Xing, Tiancheng Zhao +3RAG Citation Faithfulness Retrieval-Augmented Generation
Binjiang Institute of Zhejiang University · Zhejiang University · Guangzhou University
Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG
May 14, 2026Riccardo Terrenzi, Maximilian von Zastrow, Serkan AyvazRAG Citation Faithfulness Data Provenance
Centre for Industrial Software, University of Southern Denmark, Alsion 2, 6400 Sønderborg, Denmark
Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
Mar 10, 2026Eeham Khan, Luis Rodriguez, Marc QueudotRAG Citation Faithfulness Retrieval-Augmented Generation
Concordia University, Montréal, QC, Canada · Centre de recherche informatique de Montréal (CRIM), Montréal, QC, Canada
Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family
Apr 25, 2025Pierre-Carl Langlais, Pavel Chizhov, Mattia Nee +6Retrieval-Augmented Generation LLM Grounding
PleIAs, Paris, France

Oct 16, 2026J/K move · Enter open · S save

MuninAI: A Self-Hosted Agentic Framework for Independent Research Groups

Markus Fischer, Jens Meiler, Matthias Elgeti

Institute for Drug Discovery, Leipzig University Medical School, Leipzig, Germany · Institute for Medical Physics and Biophysics, Leipzig University Medical School, Leipzig, Germany · Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Dresden/Leipzig, Germany+3

Scientific QA Agentic RAG RAG Citation Faithfulness LLM Evaluation

Open paper AskPDF arXiv

Research groups that want a language model grounded in their own literature face a choice between hosted services that receive their unpublished work and self-hosted deployments that keep the data local but give the model no access to the corpus. Munin is an open-source framework for a self-hosted scientific assistant that indexes a group's corpus and its citation graph, and wraps whichever open-weight model the group can serve in an agent harness with specialised reading, search, and computation tools. We claim that the harness, rather than the specific model, is what makes the system useful on domain literature, and we ship the evaluation suite that tests this claim with the software. On 199 paired literature questions, the harness more than doubles the accuracy of the base model, from 0.387 to 0.874 (+0.487, 95% CI [0.407, 0.568]), while naive retrieve-then-answer scores below the unaided model on every backbone tested. Under the harness, roughly twice as many answer claims trace to a passage the model read itself as with fixed top-5 retrieval. When the source paper for a question is removed from the corpus, the system abstains on about nine in ten of the questions it had answered correctly on the Qwen backbones and eight in ten on gpt-oss-20b, and it produces no fabricated local citation across 300 fabricated references. The pattern holds on three backbones from two developers, including a 20-billion-parameter model that runs on a single consumer-grade GPU. With all outbound network access disabled, both Qwen backbones still exceed the published PaperQA2 accuracy. The evaluation suite runs as a single command, so an adopting group can re-run it on its own corpus and model.