让大模型先推理再回答，提升视觉问答准确率
Rationale-guided Prompting for Knowledge-based Visual Question Answering
- 用思维链引导模型生成中间推理过程
- 在OK-VQA和A-OKVQA上分别提升2.2和2.1分
- 适合需要可解释性推理的视觉问答任务
近期大型语言模型（LLMs）被用于知识型视觉问答（VQA）。尽管已有研究取得令人鼓舞的结果，但以往方法直接提示模型预测答案，忽略了中间思考过程。我们认为这些方法未能充分激活LLMs的能力。为此，我们提出PLRH框架，通过推理启发式（Rationale Heuristics）提示LLMs进行知识型VQA。PLRH首先引导LLMs生成思维链（CoT），得到中间推理过程，再利用该推理过程激发模型预测最终答案。实验表明，本方法在OK-VQA和A-OKVQA上的表现优于现有基线超过2.2分和2.1分。
原文摘要 · Abstract (English)
Recently, Large Language Models (LLMs) have been used for knowledge-based Visual Question Answering (VQA). Despite the encouraging results of previous studies, prior methods prompt LLMs to predict answers directly, neglecting intermediate thought processes. We argue that prior methods do not sufficiently activate the capacities of LLMs. We propose a framework called PLRH that Prompts LLMs with Rationale Heuristics for knowledge-based VQA. The PLRH prompts LLMs with Chain of Thought (CoT) to generate rationale heuristics, i.e., intermediate thought processes, and then leverages the rationale heuristics to inspire LLMs to predict answers. Experiments show that our approach outperforms the existing baselines by more than 2.2 and 2.1 on OK-VQA and A-OKVQA, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。