finding

active

finding:multimodal-cot-with-vision-features-achieves-higher-validation-accuracy-at-early-training-epochs-epoch-1-3-compared-to-one-stage-and-two-stage-language-only-baselines-on-scienceqa

Multimodal-CoT with vision features achieves higher validation accuracy at early training epochs (epoch 1-3) compared to one-stage and two-stage language-only baselines on ScienceQA

Evidence that multimodal information accelerates convergence speed during training.

Source paper

extracted_from

Multimodal Chain-of-Thought Reasoning in Language Models

(2023) · Zhuosheng Zhang · Aston Zhang · Mu Li · Hai Zhao +2

Neighborhood — ranked by edge-count

Communities (3)

community

Chain-of-Thought reasoning robustness & safety
members_of
CoT effects on generalization, multimodal QA accuracy, and AI safety alignment training.
Chain-of-thought reasoning across modalities
members_of
Demonstrates CoT effectiveness in multimodal contexts (vision+language) and few-shot settings, with ScienceQA as primary benchmark, circa 2023.
Multimodal Chain-of-Thought Reasoning
members_of
Two-stage rationale-then-answer framework evaluated on ScienceQA benchmark, ~738M parameters.

Frameworks (1)

framework

Multimodal-CoT
supports
A two-stage framework that separates rationale generation and answer inference by incorporating vision and language modalities.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Multimodal-CoT trained with InstructBLIP/ChatGPT-generated rationales achieves 87.76% accuracy on ScienceQA, comparable to human-annotated rationale performance of 90.45%finding0.850
Evidence that Multimodal-CoT can operate without human-annotated reasoning chains by using large models to generate pseudo-rationales.
One-stage CoT (QCM→RA) shows 12.31% accuracy drop vs. no-CoT (QCM→A) on ScienceQA; two-stage framework (rationale generation + answer inference) achieves 85.31% accuracy with vision featuresfinding0.820
Empirical evidence that naive one-stage CoT fails in language-only setting; two-stage + vision achieves state-of-the-art.
90.45% accuracy on ScienceQA benchmark with Multimodal-CoT Large (738M parameters)finding0.801
State-of-the-art result on ScienceQA; represents +3.91% improvement over prior best published result of 86.54%.
On GPQA-Diamond multihop questions, activation probes show genuine belief shifts during CoT generation rather than early stabilization, contrasting with MMLUfinding0.773
Empirical finding contrasting difficult questions with easy ones, supporting genuine reasoning on hard tasks
Task difficulty moderates whether CoT is performative or genuine: easy recall questions show performative CoT, difficult multihop questions show genuine reasoningclaim0.771
Task difficulty as the key variable distinguishing the two modes of CoT identified in the paper
VS-CoT and VS-Multi push the Pareto front of the diversity-quality trade-off across creative writing tasksclaim0.762
Empirical finding from creative writing experiments showing VS variants achieve higher diversity without sacrificing quality
Why do 1B-models fail at generating CoT that aids answer inference, and how can this be addressed in multimodal settings?question0.762
Central research question motivating investigation into hallucination and two-stage framework design.
The multiscale competency architecture (MCA) speeds evolutionary search by providing generalization, reliability, tractable search space, cryptic variation, and functional intermediates.claim0.762
Main functional claim about MCA.