Metraipolis › archive › dc_4af474e2b306
Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering — arXiv:2609.12230
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12230
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:03:14.510Z
- SHA-256 of the archived text
6b7145b7e6eb4fee05eedfdef9191d1656d1190ada4f91134bd34173e94ba4de- Stable URL of this page
https://metraipolis.com/documento/dc_4af474e2b306
How to cite
Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering — arXiv:2609.12230 — arXiv (en), https://arxiv.org/abs/2609.12230 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4af474e2b306 (Metraipolis archive dc_4af474e2b306, sha256 6b7145b7e6eb4fee05eedfdef9191d1656d1190ada4f91134bd34173e94ba4de)
BibTeX
@misc{dc4af474e2b306,
title = {Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering — arXiv:2609.12230},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12230},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4af474e2b306; sha256 6b7145b7e6eb4fee05eedfdef9191d1656d1190ada4f91134bd34173e94ba4de},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12230. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Question-answering often requires reasoning across multiple connected facts rather than retrieving a single isolated relation. Knowledge graphs (KGs) provide a structured way to represent such facts, but training large language models (LLMs) only on isolated KG head-relation-tail triples may limit their ability to learn the surrounding context needed for multi-hop reasoning. In this work, we propose a context-augmented training framework for multi-hop question-answering. Although generally applicable, we validate the framework in the context of disease-specific KGs, extracted using a reliable KG extraction framework called GraphMERT, for Gastroparesis and Diabetes. For each primary KG triple, we attach supporting triples extracted from the same source text chunk to form a context graph (CG). This creates two supervision settings: KG-grounded supervision, which uses only the target KG triple or path, and CG-grounded supervision, which uses the target KG triple or path together with supporting context triples. We train the Qwen3-14B model using supervised fine-tuning (SFT) under both settings, producing KGModel and CGModel variants. To strengthen the lower-hop factual foundation of the models, we introduce an LLM-judged, history-aware adaptive repair pipeline that identifies unresolved one-hop failures, continually fine-tunes on targeted repair examples, and removes or quarantines problematic noisy triples. This repair stage enables the models to reach 100% accuracy on the cleaned retained one-hop validation sets. Finally, we employ reinforcement learning (RL) using lower-hop question-answer items and evaluate generalization on harder 3-hop, 4-hop, and 5-hop tasks. Across both diseases, context-augmented supervision consistently improves multi-hop performance over KG-only supervision. RL initialized from repaired SFT checkpoints yields larger and more stable gains. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.12230 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T02:51:27.879Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).