--- title: "GROUNDEDKG-RAG — paper by Zhang and Marfurt (2026)" description: "Zhang and Marfurt propose GroundedKG-RAG, which builds its index with linguistic parsers instead of LLM summaries. 4 references." authors: ["Tianyi Zhang", "Andreas Marfurt"] year: 2026 venue: "Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26" source: "https://aclanthology.org/2026.kallm-1.7/" doi: "10.63317/3zwghvxm2rqk" licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)" licence_url: "https://creativecommons.org/licenses/by-nc/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-groundedkg-rag-grounded-knowledge-graph/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-groundedkg-rag-grounded-knowledge-graph/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/35/) / GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering # GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering **Authors:** [Tianyi Zhang](https://md.research.elamur.ai/free/en/authors/tianyi-zhang/) and Andreas Marfurt · **Year:** 2026 · **Venue:** [Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26](https://md.research.elamur.ai/free/en/venues/kallm/) ([Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26 2026](https://md.research.elamur.ai/free/en/venues/kallm/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.kallm-1.7/) · [PDF](https://aclanthology.org/2026.kallm-1.7.pdf) · [DOI 10.63317/3zwghvxm2rqk](https://doi.org/10.63317/3zwghvxm2rqk) · [OpenAlex](https://openalex.org/W7166519171) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary Long-document question answering with RAG often depends on graph or tree indexes that LLMs build by summarizing text chunks, entities and communities. Systems like GraphRAG and RAPTOR work this way. They are expensive and slow, repeat content across hierarchy levels, and can hallucinate because their summaries are not tied to the source. Zhang and Marfurt propose GroundedKG-RAG, which builds its index with linguistic parsers instead of LLM summaries. Sentences are parsed with SRL or AMR into a directed graph. Entities and actions become nodes. PropBank-style semantic roles and the temporal order of actions become edges. Every node and edge keeps links to the sentences it was extracted from. Nodes are embedded together with their graph neighbourhood. At query time, the question goes through the same parsing step, matching nodes are found, and their grounded sentences are filtered and passed to an interchangeable answer-generating LLM. On NarrativeQA examples, the system matches a state-of-the-art proprietary long-context model at lower cost and beats GraphRAG on every metric. Because the index is human-readable, auditing and error analysis are easier. ## Key points - **Graph structure:** two node types (entity, action) and two edge types (action–entity semantic roles such as A0–A3, plus temporal "next" links between actions). Each element stores its grounding sentences. - **Graph construction:** two variants, one built from SRL parses and one from AMR parses. - **Node embeddings:** three variants are compared: basic, averaged neighbours, and attention-weighted neighbours. - **Evaluation:** NarrativeQA, scored with Exact Match, Sequence Match, BERTScore and ROUGE-L F1, against a GraphRAG baseline using the same LLM. The appendix includes a sentence-count ablation on *Robinson Crusoe*. - **Error analysis:** run on *The Tale of Peter Rabbit*, it identifies three error types: failed node matching, distracting retrieved sentences, and reasoning over long, similar contexts. Source code is available on request. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Lucerne University of Applied Sciences and Arts](https://md.research.elamur.ai/free/en/universities/lucerne-university-of-applied-sciences-and-arts/) — University, Lucerne, Switzerland · 2 works · 1 citation 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works 🧭 Topics (2): [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 487 works · [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) · 211 works ## Cite Cite as: Tianyi Zhang and Andreas Marfurt. 2026. GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering. Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{zhang2026groundedkg, title = {{GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering}}, author = {Tianyi Zhang and Andreas Marfurt}, booktitle = {Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26}, year = {2026}, doi = {10.63317/3zwghvxm2rqk}, url = {https://doi.org/10.63317/3zwghvxm2rqk} } ``` - [← previous Grounded Multimodal In-Context Learning for Product Weight Estimation at Scale in E-commerce](https://md.research.elamur.ai/free/en/papers/singhal-2026-grounded-multimodal-context-learning-product/) - [next → Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith](https://md.research.elamur.ai/free/en/papers/eltanbouly-2026-grounding-arabic-llms-doha-historical/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/35/) ## References 4 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. V.A. Traag, L. Waltman, and N.J. van Eck. 2019. From louvain to leiden: guaranteeing well-connected communities. In Sci Rep 9, 5233. [find](https://scholar.google.com/scholar?q=V%2EA%2E+Traag%2C+L%2E+Waltman%2C+and+N%2EJ%2E+van+Eck%2E+2019%2E+From+louvain+to+leiden%3A+guaranteeing+well%2Dconnected+communities%2E+In+Sci+Rep+9%2C+5233%2E) 2. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2025. From local to global: A graph rag approach to query-focused summarization. [find](https://scholar.google.com/scholar?q=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+Dasha+Metropolitansky%2C+Robert+Osazuwa+Ness%2C+and+Jonathan+Larson%2E+2025%2E+From+local+to+global%3A+A+graph+rag+app) 3. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. [find](https://scholar.google.com/scholar?q=Tianyi+Zhang%2C+Varsha+Kishore%2C+Felix+Wu%2C+Kilian+Q%2E+Weinberger%2C+and+Yoav+Artzi%2E+2020%2E+Bertscore%3A+Evaluating+text+generation+with+bert%2E) 4. Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, and Chao Huang. 2025. [LightRAG: Simple and fast retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/guo-2024-lightrag-simple-fast-retrieval-augmented/). In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 10746–10761, Suzhou, China. Association for Computational Linguistics. *Updated 2 November 2026*