Metraipolis › archive › dc_35fc9f5a7841
DARE: Dialectical Agentic Reasoning for Structured Knowledge Fact Checking — arXiv:2609.13808
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13808
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T23:14:37.781Z
- SHA-256 of the archived text
869dda1bae2468c7f4983db62a9fe734f67fd887dca9fa4051a5e467e171faa7- Stable URL of this page
https://metraipolis.com/documento/dc_35fc9f5a7841
How to cite
DARE: Dialectical Agentic Reasoning for Structured Knowledge Fact Checking — arXiv:2609.13808 — arXiv (en), https://arxiv.org/abs/2609.13808 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35fc9f5a7841 (Metraipolis archive dc_35fc9f5a7841, sha256 869dda1bae2468c7f4983db62a9fe734f67fd887dca9fa4051a5e467e171faa7)
BibTeX
@misc{dc35fc9f5a7841,
title = {DARE: Dialectical Agentic Reasoning for Structured Knowledge Fact Checking — arXiv:2609.13808},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13808},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35fc9f5a7841; sha256 869dda1bae2468c7f4983db62a9fe734f67fd887dca9fa4051a5e467e171faa7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13808. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Structured knowledge fact checking aims to determine the truthfulness of natural language claims by reasoning over structured evidence. Recent program-generation approaches leverage large language models (LLMs) to generate executable graph reasoning programs, achieving strong performance on structured knowledge fact checking benchmarks. However, these methods remain limited by invalid relation generation, single-path reasoning that lacks self-correction, and biased evidence assessment that tends to overestimate supporting signals. We propose Dialectical Agentic Reasoning (DARE), a multi-agent framework that formulates structured knowledge fact checking as an iterative retrieve-reason-reflect process. DARE integrates relation-grounded evidence retrieval to constrain reasoning to valid structures, dialectical bidirectional verification to evaluate evidence from both supporting and refuting perspectives, and confidence-driven meta-reflection to dynamically determine whether additional evidence exploration is necessary. Extensive experiments demonstrate the effectiveness of DARE in structured knowledge fact checking, with an 8B backbone achieving 88.12% accuracy and matching or surpassing GPT-4o-based program-generation baselines, which attests to the efficacy of dialectical agentic reasoning in eliciting the latent reasoning capabilities of LLMs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.13808 — 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 2026-10-15T22:51:09.840Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).