Metraipolis › archive › dc_3be5e07bf279
On the LLM Verification for Argument Graph Generation — arXiv:2610.27361
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.27361
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:08:53.372Z
- SHA-256 of the archived text
e9cac1b072b8d9d3d46c547edfc45f562bf1e68ffffd2574fea5bedfdd60ee51- Stable URL of this page
https://metraipolis.com/documento/dc_3be5e07bf279
How to cite
On the LLM Verification for Argument Graph Generation — arXiv:2610.27361 — arXiv (en), https://arxiv.org/abs/2610.27361 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3be5e07bf279 (Metraipolis archive dc_3be5e07bf279, sha256 e9cac1b072b8d9d3d46c547edfc45f562bf1e68ffffd2574fea5bedfdd60ee51)
BibTeX
@misc{dc3be5e07bf279,
title = {On the LLM Verification for Argument Graph Generation — arXiv:2610.27361},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.27361},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3be5e07bf279; sha256 e9cac1b072b8d9d3d46c547edfc45f562bf1e68ffffd2574fea5bedfdd60ee51},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27361. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent LLM systems can formalize natural-language argumentation end-to-end, turning plain text into structured graphs by classifying components, connecting them with relations, and enriching the resulting graphs into formal models. Quality assurance for those graphs is almost always another LLMs: a reviewer, judge, or critic agent. On the other side, in adjacent neuro-symbolic fields, such generated output is often verified symbolically by external checks and solvers. In this work, we argue that in argument graph verification, the allocation should be similar, and based on what each instrument can guarantee. We propose layered verification: starting from deterministic checks, moving to solver-based and LLM reviews, and utilizing debate only under uncertainty, leaving human judgment for what no other instrument can decide. We ground our principle with a study on human-annotated graphs with injected structural defects. An LLM reviewer detects them at near-ceiling recall, including cycles in the support relation, but it objects to almost one in a ten correct graphs, even though it should not, happens to be inconsistent in verdict on identical inputs and is significantly slower than the equivalent exact check. It shows that while LLM reviewer does not lack the ability to detect structural defects, it is worth having a deterministic verification gates. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.27361 — 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 2026-10-21T07:05:58.111Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).