Metraipolis › archive › dc_ea26f57c44c5
TriQua: Reconciling Granularity and Context in Factuality Evaluation — arXiv:2608.05228
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05228
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T21:27:29.830Z
- SHA-256 of the archived text
ea27cb4b5aeb8a71e03e1b5cde0ece3d4c39302043c94779be952e95eff8526b- Stable URL of this page
https://metraipolis.com/documento/dc_ea26f57c44c5
How to cite
TriQua: Reconciling Granularity and Context in Factuality Evaluation — arXiv:2608.05228 — arXiv (en), https://arxiv.org/abs/2608.05228 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea26f57c44c5 (Metraipolis archive dc_ea26f57c44c5, sha256 ea27cb4b5aeb8a71e03e1b5cde0ece3d4c39302043c94779be952e95eff8526b)
BibTeX
@misc{dcea26f57c44c5,
title = {TriQua: Reconciling Granularity and Context in Factuality Evaluation — arXiv:2608.05228},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05228},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea26f57c44c5; sha256 ea27cb4b5aeb8a71e03e1b5cde0ece3d4c39302043c94779be952e95eff8526b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05228. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The "decompose-then-verify" paradigm for LLM factuality evaluation faces a fundamental trade-off: atomic facts, i.e., one sentence conveying one unit of information, often omit essential context, while broader statements lack the granularity needed for precise assessment. To address this, we introduce TriQua, a framework that flexibly models facts based on their complexity. Simple claims are extracted as standard triples, while complex claims are represented as hyperrelational facts by attaching auxiliary contextual qualifiers. This adaptive structure preserves the necessary context for accurate retrieval and verification without sacrificing atomicity. Furthermore, TriQua's verification process directly annotates concrete errors within specific triples and qualifiers, providing fine-grained explainability for error detection. Alongside the framework, we propose TriQuaScore to quantify the factuality of these structured fact units. Empirical evaluations show that TriQuaScore strongly aligns with human annotated factuality scores, TriQua achieves robust decomposition quality, and outperforms existing decomposition-based frameworks in evidence-based fact verification. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.05228 — 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 2026-10-25T21:24:38.242Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).