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
75 results for “keyword:"probe"” in ICLR 2027. 4 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Content-Matched Is Not Lexically Matched: Text and Untrained-Network Baselines for Evaluation-Awareness Probing▼4.5k2.67
[PDF]The Verbalization Gap: Stress-Testing Activation Monitoring with Natural Language Autoencoders▼1351.33
[PDF]From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models▼1351.33
[PDF]Misaligned model variants serve as an effective source of training for harm detection probes▲5103.00
[PDF]Rescuing Points Trapped Inside Incorrect Decision Regions: A target for Evaluating and Improving Forward-Forward Learning▲5103.00
[PDF]Transformers develop separable posterior and value representations in a simple decision task▼4.3k2.00
[PDF]Same Data, Different Target: How the Prediction Target Can Separate Probing from Steering▼1.2k1.67
[PDF]Linear Lobotomy For Alien Graph Representations : Probing, Ablation and Recovery of Linear Features in Graph Neural Networks▼4.3k2.00
[PDF]Routing-Guided Single-Expert Interventions Measured Against a Model’s Own Execution Variability▲6.1k2.00
[PDF]GLCR: Global-Local Complementary Representations for Wi-Fi Probe Request Association under MAC Randomization▼4.5k2.67
[PDF]Frozen Input-Harm Probes under Compression: Retained AUROC Does Not Mean Retained Refusal▼1.2k1.67
[PDF]Affective Representations of Large Language Models Differ Between AI-Centric and Human-Centric Scenarios▼5.9k2.60