Metraipolis › archive › dc_157eda91b52e

HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews — arXiv:2609.03580

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03580
License (as archived)
CC0-1.0
Archived
2026-10-17T01:11:01.504Z
SHA-256 of the archived text
88204e76c058b8a8baced0265bd1a9a97f489b60d2512ca3add8f6a4966a4309
Stable URL of this page
https://metraipolis.com/documento/dc_157eda91b52e

How to cite

HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews — arXiv:2609.03580 — arXiv (en), https://arxiv.org/abs/2609.03580 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_157eda91b52e (Metraipolis archive dc_157eda91b52e, sha256 88204e76c058b8a8baced0265bd1a9a97f489b60d2512ca3add8f6a4966a4309)
BibTeX
@misc{dc157eda91b52e,
  title = {HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews — arXiv:2609.03580},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03580},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_157eda91b52e; sha256 88204e76c058b8a8baced0265bd1a9a97f489b60d2512ca3add8f6a4966a4309},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03580. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The growing scale of academic peer review has motivated the use of Large Language Models (LLMs) as review assistants, yet LLMs can generate fluent but unsupported claims that undermine review reliability. Existing hallucination benchmarks are not designed for peer review, where verification requires grounding claims in long, technical papers. We introduce HalluPeer, a benchmark for detecting hallucinations in scientific peer reviews, providing aligned triples of paper content, human-written reviews, and hallucination-injected reviews, annotated for detection, classification, and localization. Our pipeline induces a peer-review-specific hallucination taxonomy, identifies review contexts, and injects hallucinations with automated filtering. Experiments on 12K papers and 38K reviews show that existing detectors struggle to separate hallucinations from legitimate critique, while evaluation on authentic reviews demonstrates that HalluPeer-defined hallucination patterns occur in real peer reviews, highlighting the critical need for source-aware verification. Our project page can be found in this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.03580 — 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 2026-10-17T00:28:02.863Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).