4 papers · 1 filter
STEP: Soft Trajectory Estimation of Prediction Correctness via Per-Step Probability Scoring
Chenyang Yu, Zifan Zeng, Qunli Zhang +1
Estimating the correctness of large language model (LLM) predictions without access to ground truth is critical for reliable deployment in high-stakes settings. Existing approaches…
LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry
Xunye Tian, Zhijian Zhou, Liuhua Peng +1
Data-adaptive two-sample testing assesses if two samples come from the same distribution, using a discrepancy learned from the data (e.g., via kernel-based feature representations)…
Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs
Ke Li, Chongzhe Zhang, Zifan Zeng +3
Large language models often express high confidence in answers that are wrong. Standard calibration remedies typically act globally or at the score level, reducing unwarranted conf…
Unlearning Evaluation through Subset Statistical Independence
Chenhao Zhang, Muxing Li, Feng Liu +2
Evaluating machine unlearning remains challenging, as existing methods typically require retraining reference models or performing membership inference attacks, both of which rely…