arXiv Machine Learning By Ziyang Luo, Zhongyao Chu, Xinjie He, Youting Wang, Xukui Qin, Runxiong Wu, Yan-Syuan Chen

You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model

Read the original on arXiv Machine Learning →

arXiv:2608. 14465v1 Announce Type: cross Abstract: A frozen language model on reasoning tasks has two coupled weaknesses: it under-uses evidence its own residual stream already encodes, and it fails to detect when the input is insufficient to answer, so it confabulates.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.