Metraipolis › archive › dc_c624528876fe

To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech — arXiv:2609.30227

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30227
License (as archived)
CC0-1.0
Archived
2026-10-08T04:28:06.097Z
SHA-256 of the archived text
03151623422cb2e21d00b62763a52fb38c846b4a6ca87e802045bf36b63c8c77
Stable URL of this page
https://metraipolis.com/documento/dc_c624528876fe

How to cite

To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech — arXiv:2609.30227 — arXiv (en), https://arxiv.org/abs/2609.30227 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c624528876fe (Metraipolis archive dc_c624528876fe, sha256 03151623422cb2e21d00b62763a52fb38c846b4a6ca87e802045bf36b63c8c77)
BibTeX
@misc{dcc624528876fe,
  title = {To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech — arXiv:2609.30227},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30227},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c624528876fe; sha256 03151623422cb2e21d00b62763a52fb38c846b4a6ca87e802045bf36b63c8c77},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30227. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VeriSpeak, a probe benchmark for studying speech-based fact verification in Large Audio Language Models (LALMs). VeriSpeak contains 3,879 spoken claims spanning temporal, geographical, and relational facts, with balanced true and false labels. The benchmark is designed to examine whether factual verification ability transfers from text to speech, and whether retrieval-augmented LALMs can use textual evidence to correctly support or refute spoken claims. Our experiments reveal a consistent text-speech modality gap: LALMs that verify written claims reliably often fail on the same claims when spoken. Moreover, retrieval alone provides limited gains because models frequently conflate retrieved evidence with the spoken claim. In contrast, retrieval combined with explicit reasoning improves claim-evidence comparison, with a thinking-tuned LALM reaching 86.1% accuracy. VeriSpeak highlights that effective speech misinformation detection requires not only speech understanding, but also grounded reasoning over retrieved evidence. The dataset is publicly available via Hugging Face at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.30227 — 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 2026-10-08T03:50:58.261Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).