Metraipolis › archive › dc_e60350dce601

Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models — arXiv:2608.22762

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.22762
License (as archived)
CC0-1.0
Archived
2026-10-18T07:41:36.455Z
SHA-256 of the archived text
baf51867057d3db05d20edc9994bad027464f64e133b42a6b2666605acf27110
Stable URL of this page
https://metraipolis.com/documento/dc_e60350dce601

How to cite

Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models — arXiv:2608.22762 — arXiv (en), https://arxiv.org/abs/2608.22762 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e60350dce601 (Metraipolis archive dc_e60350dce601, sha256 baf51867057d3db05d20edc9994bad027464f64e133b42a6b2666605acf27110)
BibTeX
@misc{dce60350dce601,
  title = {Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models — arXiv:2608.22762},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22762},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e60350dce601; sha256 baf51867057d3db05d20edc9994bad027464f64e133b42a6b2666605acf27110},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22762. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large Language Models (LLMs), and complex KGQA that requires multi-hop reasoning is especially challenging. Solving a complex query involves two coupled phases: candidate retrieval, which locates answer candidates over the KG, and constraint handling, which filters these candidates against the query constraints. Faithful reasoning requires grounding both phases in the KG. However, existing agent-based methods ground candidate retrieval through entity-centric exploration, while leaving constraint handling to the LLM's internal knowledge, which leads to two critical limitations. (1) Unreliable entity pruning: entity-centric exploration uses entities as search units and must prune them to a fixed-size subset at each hop. Because entity information in KGs is often incomplete and a fixed-size subset cannot retain all valid entities, such pruning inevitably drops valid entities and ultimately leads to wrong answers. (2) Ungrounded constraint handling: query constraints are resolved from the LLM's internal knowledge rather than the KG, leaving the final answers unverifiable and prone to hallucination. To address these limitations, this paper introduces a relation-centric exploration paradigm, which uses relations rather than entities as search units and thus avoids unreliable entity pruning. Built on this paradigm, this paper proposes Compositional Chain-of-Relations (CCoR), a simple and effective framework that grounds both phases in the KG with two relation chains: a main chain for candidate retrieval and a constraint chain that verifies query constraints through explicit KG exploration. Experiments on four KGQA benchmarks show that CCoR consistently improves accuracy, faithfulness, and efficiency over strong baselines, with more pronounced gains on complex queries.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.22762 — 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 2026-10-18T07:37:52.739Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).