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
140 results for “keyword:"confidence"” in ICLR 2027. 38 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CONFIDENCE-GATED DISTILLATION OF LANGUAGE MODEL SEMANTICS FOR COLD-START RECOMMENDATION▼1.3k1.80
[PDF]Maximin-Sufficient Learning under Strategic Feedback in Zero-Sum Games with an Informed Opponent▼4.3k2.00
[PDF]Confidence Is Not Enough: Decision-Value Finding Selection Beats Confidence-Gated Test-Time Compute▲3952.67
[PDF]One Schedule Does Not Fit All: Adaptive Inference Schedules for Diffusion Language Models▼4.3k2.00
[PDF]DCLED: Dynamic Confidence-Aware Layer-wise Evolution Decoding for Factuality-Oriented Candidate Scoring▼4.3k2.00
[PDF]AdaptEvo: Learning under Imperfect Supervision through Confidence-Adaptive Training with Knowledge Evolution▼4.3k2.00
[PDF]Beyond Binary Correctness: Confidence Estimation for Continuously Graded Responses in Large Language Models▲3952.67
[PDF]When Is Calibrated Confidence Sufficient for Optimal Stopping in Sequential Prediction?▲3.9k1.67
[PDF]Not All Teachers Are Created Equal: Confidence-Aware Prediction-Powered Learning from Heterogeneous Teachers▼5.8k2.33
[PDF]Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents▲3.0k2.50
[PDF]Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs▼1.2k1.67
[PDF]RNAStructFold: MSA-free RNA 3D Structure Prediction via RNA Language-Model Attention Priors▲11.00
[PDF]Constant-Rank Confidence Amplification for Parameter-Free Heavy-Tailed Graph-Unimodal Bandits▼4.3k2.00
[PDF]Auditing Early Stopping after Deployment: Sequential Inference with Selective Feedback▲3.0k2.33
[PDF]DUEL: Exact Likelihood for Masked Diffusion Reveals Improved Pre-Training Scaling Laws▼4.5k2.67
Withdrawn or desk rejected (38)
[PDF]The Interface Is the Policy: Output Typing, Calibration, and Confidence-Gated Routing in LLM Trading AgentsDesk rejected1.00
[PDF]Commit Order, Not Commit Rate: Answer Availability and Prefix Preservation in Diffusion Language ModelsWithdrawn1.67
[PDF]LACS: Distribution-Sensitive Label-Agnostic Confidence Selection for Dynamic Data PruningDesk rejected
[PDF]FedCrossID: Recovering Fragmented Cross-Camera Supervision in Federated Person Re-IdentificationWithdrawn1.67
[PDF]Teaching Language Models to Say What They Know: Reinforcement Learning with Internal Confidence AlignmentWithdrawn2.00