OpenReviewer, a fine-tuned Llama-3.1-8B model trained on 79,000 expert reviews, generates more critical and human-aligned paper reviews than GPT-4o and Claude-3.5.
The other two expert reviews rated it as 8 and 3, so this rating is within the range of expert opinions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews
OpenReviewer, a fine-tuned Llama-3.1-8B model trained on 79,000 expert reviews, generates more critical and human-aligned paper reviews than GPT-4o and Claude-3.5.