mlsanityData to 14 Oct 2026

EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language Models

arXiv 2609.00479 ↗First posted 31 Aug 2026cs.AIcited by 0

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

For emerging scientific research domains, local Small Language Models (SLMs) are becoming more attractive, as they offer stronger privacy control and more stable deployment pipelines than Large Language Models. However, in practice, scientific question-answering on SLMs often operates under inevitable constraints: small literature collections, fragmented evidence, limited context window and reasoning abilities. We propose the Evidence-Grounded Typed Knowledge Graph (EGT-KG), a retrieval framework to improve information retrieval with local SLMs. We assessed three question-answering settings: a vanilla Retrieval-Augmented Generation (RAG) workflow and two EGT-KG workflows: an automatically generated relation schema (AS) and an expert-defined relation schema (ES). Our experiments were evaluated with a six-dimensional evaluation framework (S3CRF: Soundness, Correctness, Completeness, Conciseness, Relevance, Fluency) on a Biopolymer-bound Soil Composite literature benchmark, showing that EGT-KG outperforms the vanilla RAG method in most settings, with the best improvement from llama3:8b: a Final Score of 70.37 (+14.67%) and 68.82 (+12.14%) by AS/ES EGT-KG variants.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 71 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

16 of 71 references.

References · 16

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  3. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  4. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  5. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 843
  6. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  7. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 486
  8. 2024Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Lawscited by 144
  9. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 127
  10. 2024Small Language Models: Survey, Measurements, and Insightscited by 112
  11. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 93
  12. 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corporacited by 49
4 more
  1. 2023AutoKG: Efficient Automated Knowledge Graph Generation for Language Modelscited by 17
  2. 2025A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Servicescited by 17
  3. 2024Automated Construction of Theme-specific Knowledge Graphscited by 16
  4. 2026Lost in the Noise: How Reasoning Models Fail with Contextual Distractorscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025KG2QA: Knowledge Graph-enhanced Retrieval-augmented Generation for Communication Standards Question Answering
  2. 2026LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering
  3. 2026From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models
  4. 2023HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses
  5. 2026Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models
  6. 2025Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
  7. 2025Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models
  8. 2026Knowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question Answering