ICLR

The ICLR dataset contains submissions to the International Conference on Learning Representations and is used to evaluate the effectiveness of a large language model in predicting the acceptance or rejection of manuscripts based on assigned quality scores.

Papers using ICLR (3)

Intelligence Is Not the Bottleneck: Validating an LLM First-Pass Manuscript Score Against Peer-Review Outcomes2026PRAIB: Peer Review AI Benchmark of Behaviour of LLM-Assisted Reviewing2026LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers2026