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
72 results for “keyword:"trustworthy"” in ICLR 2027. 37 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Certify Before You Intervene: Pathwise Intervention-Certified Decoding for Multimodal Generation▼5.8k2.33
[PDF]Are Foundation Models Enough for Data-Scarce Functional Connectivity Diagnosis? Revisiting Task-Specific Learning with BrainLRR▼4.5k2.67
[PDF]HDIR: Training-free Hallucination Detection via Discriminative Internal Representations▼1.2k1.67
[PDF]Beyond the Best Available Cause: Calibrated Verification and Triage under Hypothesis-Space Inadequacy▲3.0k2.33
[PDF]CAVCD: Candidate-Aware Visual Counterfactual Decoding for Mitigating Object Hallucinations in Large Vision-Language Models▼1611.50
Withdrawn or desk rejected (37)
[PDF]Attested but Unaccounted: DP-SGD Privacy Accounting as a Precondition of Every StepWithdrawn1.67
[PDF]Teaching Language Models to Say What They Know: Reinforcement Learning with Internal Confidence AlignmentWithdrawn2.00
[PDF]SHERLOC: Statistical Hypothesis Evaluation and Recovery for Learning Opponent CharacteristicsWithdrawn1.67
[PDF]From Scores to Evidence: A Framework for Epistemically Valid Evaluation of LLM Coding AgeDesk rejected