Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Compositional Chain-of-Thought Prompting for Large Multimodal Models

About

The combination of strong visual backbones and Large Language Model (LLM) reasoning has led to Large Multimodal Models (LMMs) becoming the current standard for a wide range of vision and language (VL) tasks. However, recent research has shown that even the most advanced LMMs still struggle to capture aspects of compositional visual reasoning, such as attributes and relationships between objects. One solution is to utilize scene graphs (SGs)--a formalization of objects and their relations and attributes that has been extensively used as a bridge between the visual and textual domains. Yet, scene graph data requires scene graph annotations, which are expensive to collect and thus not easily scalable. Moreover, finetuning an LMM based on SG data can lead to catastrophic forgetting of the pretraining objective. To overcome this, inspired by chain-of-thought methods, we propose Compositional Chain-of-Thought (CCoT), a novel zero-shot Chain-of-Thought prompting method that utilizes SG representations in order to extract compositional knowledge from an LMM. Specifically, we first generate an SG using the LMM, and then use that SG in the prompt to produce a response. Through extensive experiments, we find that the proposed CCoT approach not only improves LMM performance on several vision and language VL compositional benchmarks but also improves the performance of several popular LMMs on general multimodal benchmarks, without the need for fine-tuning or annotated ground-truth SGs. Code: https://github.com/chancharikmitra/CCoT

Chancharik Mitra, Brandon Huang, Trevor Darrell, Roei Herzig• 2023

Related benchmarks

TaskDatasetResultRank
Visual Question AnsweringVizWiz
Accuracy57.5
1863
Visual Question AnsweringTextVQA
Accuracy61.1
1455
Visual Question AnsweringGQA
Accuracy63.1
1445
Visual Question AnsweringVQA v2
Accuracy80.3
1429
Science Question AnsweringScienceQA
Accuracy86.3
916
Multimodal ReasoningMM-Vet
MM-Vet Score36.1
551
Visual Question AnsweringScienceQA
Accuracy77.1
525
Mathematical ReasoningMathVista
Accuracy57.8
382
Multimodal ReasoningMMBench--
180
Visual Question AnsweringMMBench (MMB)
Accuracy69.2
169
Showing 10 of 89 rows
...

Other info

Code

Follow for update