决策前先观察:提示多模态大语言模型主动演绎以实现假设推理
Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning
AI总结:
针对多模态大语言模型(MLLMs)是否具备类人组合推理能力的问题,本文构建MARS-Bench基准,提出主动演绎(AD)强化学习方法,提升MLLMs假设推理能力且不影响通用问答性能。
摘要:
近年来,多模态大语言模型(MLLMs)凭借出色的指令遵循能力和丰富的世界知识,在多个学科取得显著成功。然而,这些MLLMs是否具备类人的组合推理能力仍是一个开放性问题。为揭示其推理行为,本文首先构建了一个多模态假设推理基准(MARS-Bench)。有趣的是,我们发现大多数主流MLLMs容易被问题中引入的预设误导,而这类预设对人类推理而言十分简单。此外,我们还提出一种简单有效的方法——主动演绎(AD),这是一种新型强化学习范式,旨在鼓励模型在做出最终决策前主动进行组合演绎。配备所提出的AD方法后,MLLM在假设推理能力上取得显著提升,同时未损害其通用问答性能。我们还在MARS-Bench上对开源和私有MLLMs进行了广泛评估,并对AD方法进行了实验分析。
英文摘要:
Recently, Multimodal Large Language Models (MLLMs) have achieved significant success across multiple disciplines due to their exceptional instruction-following capabilities and extensive world knowledge. However, whether these MLLMs possess human-like compositional reasoning abilities remains an open problem. To unveil their reasoning behaviors, we first curate a \textbf{M}ultimodal \textbf{A}ssumptive \textbf{R}ea\textbf{s}oning Benchmark (MARS-Bench) in this paper. Interestingly, we find that most prevalent MLLMs can be easily fooled by the introduction of a presupposition into the question, whereas such presuppositions appear naive to human reasoning. Besides, we also propose a simple yet effective method, Active Deduction (AD), a novel reinforcement learning paradigm to encourage the model to actively perform composite deduction before reaching a final decision. Equipped with the proposed AD method, a MLLM demonstrates significant improvements in assumptive reasoning abilities without compromising its general-purpose question-answering performance. We also provide extensive evaluations of both open-source and private MLLMs on MARS-Bench, along with experimental analyses of the AD method.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。