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
185 results for “keyword:"lm evaluation"” in ICLR 2027. 30 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]How Much Evaluation Is Enough? Risk-Aware Adaptive Evaluation (RAAE) of LLMs in High-Stakes Financial Applications▼1361.33
[PDF]The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures▼1.2k1.67
[PDF]Do LLMs Follow a Behavioral SCRIPT? Measuring Structural Choreography and Rigidity from Positions and Transitions▲3952.67
[PDF]What Do Benchmarks Measure? Discovering Benchmark Demands and Grounding System Capabilities▲20k2.67
[PDF]Design, Not Noise: Certifying Cross-Model Claims in Black-Box Behavioural Audits of Language Models▲6.1k2.00
[PDF]What Reviewers Catch and Frontier Models Miss: Statement-Level Errors in Autoformalization▲6.1k2.00
[PDF]Capability Calibration in Role-Playing Language Models: A Benchmark and Metacognitive Agentic Framework▲3.0k2.33
[PDF]Consensus Need Not Be Evidence: Information Limits and Adaptive Auditing for Multi-LLM Evaluation▲3952.67
[PDF]Did the Model Get Better or Just Different? Directional Evaluation of LLM Updates from Unlabeled Probes▼1.2k1.67
[PDF]What does lie-detection accuracy measure? An Identification Audit of behavioural LLM deception benchmarks▼71.25
[PDF]AeroProc-Bench: Distinct Citation and Safety Failures Create a Deployment Dilemma in Aviation Maintenance LLMs▲11.00
[PDF]Generation and Judgment Diverge in Code Models: A Matched Benchmark with Derived Ground Truth▲3.9k1.67
[PDF]FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence▲5103.00
Withdrawn or desk rejected (30)
[PDF]ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive EvaluationDesk rejected2.00
[PDF]Ace Olympiad Math, Fail Simple Arithmetic: Systematic Capability Unreliability in LLMsDesk rejected
[PDF]Smaller Than the Noise: A Measurement-Theoretic Audit of Evaluation Protocols for LLMsWithdrawn1.33
[PDF]When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey ResponsesWithdrawn1.33
[PDF]Validating Rankings from Pairwise ComparisonsDesk rejected