NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
18 results for “keyword:"item response"” in ICLR 2027. 5 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Rubric-Calibrated Preferences: Cross-Query Calibration of LLM Judgments via Item Response Theory▼4.5k2.67
[PDF]What Can Be Corrected in LLM Judge Ratings? Identifiability, Measurement, and Targeted Adjustment▼4.3k2.00
[PDF]SkillEval: Learning Interpretable Ability Profiles of LLMs via Cognitive Diagnosis Models▼1.2k1.67
[PDF]Rethinking Item Response Theory for LLM Evaluation with Item-Marginalized Maximum Likelihood▼2433.33
Withdrawn or desk rejected (5)
[PDF]Can We Make an LLM Dumber, or Is It Just Playing Dumb? An Empirical Study of Believable Performance ThrottlingWithdrawn1.67
[PDF]DECAF: Disentangling Capability and Translation Artifacts for Multilingual LLM EvaluationWithdrawn1.67