Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models

arXiv:2403.17359v1 Announce Type: new
Abstract: We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA). Compared to the literature, CoA overcomes two major challenges of current QA applications: (i) unfaithful hallucination that is inconsistent with real-time or domain facts and (ii) weak reasoning performance over compositional information. Our key contribution is a novel reasoning-retrieval mechanism that decomposes a complex question into a reasoning chain via systematic prompting and pre-designed actions. Methodologically, we propose three types of domain-adaptable `Plug-and-Play' …

abstract applications arxiv challenges cs.cl current domain facts framework hallucination information language language models large language large language models literature major multimodal performance question question answering real-time reasoning retrieval retrieval-augmented through type