Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs
Beier Luo, Cheng Wang, Hongxin Wei +2
Post-training improves large language models (LLMs) but often worsens confidence calibration, leading to systematic overconfidence. Recent unsupervised post-hoc methods for post-tr…
cs.LG2026
Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping
Jianxiong Zhang, Bing Guo, Yuming Jiang +3
Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination detection challenging. Although tra…