Pith. sign in

REVIEW 2 cited by

Compositional Chain-of-Thought Prompting for Large Multimodal Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.17076 v3 pith:C4WQ2B7Q submitted 2023-11-27 cs.CV cs.AIcs.CLcs.LG

classification cs.CVcs.AIcs.CLcs.LG
keywords compositionalchain-of-thoughtccotlanguagelargelmmsmultimodalscene
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning

    cs.AI 2025-05 conditional novelty 6.0 of 10

    Drawing an AI's step-by-step position onto video frames, alongside text reasoning, improves its accuracy on dynamic maze-judgment and maze-navigation tasks.

  2. Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning

    cs.CV 2025-07 conditional novelty 4.0 of 10

    Scene-graph-based chain-of-thought prompting and GRPO training improve spatial reasoning accuracy in vision-language models, and GRPO degrades less than supervised fine-tuning when question wording is flipped.

Pith tools