← 研踪 PaperTrailarXiv:2110.08294 · v3
Coherence boosting: When your pretrained language model is not paying enough attention
首次提交 2021-10-16 02:05
版本更新 2026-11-19 00:36
雷达观测 2026-11-19 15:04
摘要
Long-range semantic coherence remains a challenge in automatic language generation and understanding. We demonstrate that large language models have insufficiently learned the effect of distant words on next-token prediction. We present coherence boosting, an inference procedure that increases a LM's focus on a long context. We show the benefits of coherence boosting with pretrained models by distributional analyses of generated ordinary text and dialog responses. It is also found that coherence boosting with state-of-the-art models for various zero-shot NLP tasks yields performance gains with no additional training.
作者备注:ACL 2022; code: https://github.com/zhenwang9102/coherence-boosting
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-19 00:36 · 最新观测版本
Coherence boosting: When your pretrained language model is not paying enough attention
Long-range semantic coherence remains a challenge in automatic language generation and understanding. We demonstrate that large language models have insufficiently learned the effect of distant words on next-token prediction. We present coherence boosting, an inference procedure that increases a LM's focus on a long context. We show the benefits of coherence boosting with pretrained models by distributional analyses of generated ordinary text and dialog responses. It is also found that coherence boosting with state-of-the-art models for various zero-shot NLP tasks yields performance gains with no additional training.
查看此版本解读 →查看此版本原文 ↗