An LLM-based review system processing 290 real submissions was far faster and cheaper than human review, yet agreed with the conference's acceptance decisions only 38.6% of the time, indicating LLMs should assist rather than replace human reviewers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can Large Language Models Be Trusted Paper Reviewers? A Feasibility Study
An LLM-based review system processing 290 real submissions was far faster and cheaper than human review, yet agreed with the conference's acceptance decisions only 38.6% of the time, indicating LLMs should assist rather than replace human reviewers.