Researcher suspects HCI authors deliberately obfuscate LLM judge use to dodge reviewers

IanArawjo · x · 2026-09-03

Following up on his observation that HCI papers obfuscate their use of LLM judges, Ian Arawjo offers a cynical motive: authors may be deliberately vague, pre-empting reviewer complaints if the LLM judge usage were disclosed. The remark sharpens the academic-norms debate around LLM-assisted evaluation.

Related event: HCI Papers Quietly Use LLM Judges, Obscuring the Fact(2 posts)→

Original post →

More from Research

Research channel →