Understanding and Patching Compositional Reasoning in LLMs

arXiv:2402.14328v1 Announce Type: new
Abstract: LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks. Our research embarks on a quest to uncover the root causes of compositional reasoning failures of LLMs, uncovering that most of them stem from the improperly generated or leveraged implicit reasoning results. Inspired by our empirical findings, we resort to Logit Lens and an intervention experiment to dissect the inner hidden states of LLMs. This deep dive reveals that implicit …

abstract arxiv cs.cl generated llms quest reasoning research shift stem tasks them type understanding