Pith. sign in

REVIEW 4 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

Compositional Chain-of-Thought Prompting for Large Multimodal Models

classification cs.CV cs.AIcs.CLcs.LG
keywords compositionalchain-of-thoughtccotlanguagelargelmmsmultimodalscene
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
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)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. From Bounding Boxes to Visual Reasoning: An On-Policy Data Annotation Tool for Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 7.0

    ScreenAnnotator introduces a unified annotation atom schema, on-policy Bayesian verification loop, and template-driven synthesis to generate reusable multi-task reasoning data for VLMs, reporting nearly 100% accept ra...

  2. Self-Prophetic Decoding to Unlock Visual Search in LVLMs

    cs.CV 2026-05 unverdicted novelty 6.0

    SeProD is a plug-and-play self-prophetic decoding framework that combines pre- and post-training LVLM capabilities via probability-based sampling to improve coherent visual search and multi-step reasoning.

  3. The Platonic Representation Hypothesis

    cs.LG 2024-05 unverdicted novelty 5.0

    Representations learned by large AI models are converging toward a shared statistical model of reality.

  4. UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning

    cs.CV 2026-05 unverdicted novelty 4.0

    UnAC improves LMM performance on visual reasoning benchmarks by combining adaptive visual prompting, image abstraction, and gradual self-checking.