# Towards Faithful Reasoning in Comics for Small MLLMs

arXiv: https://arxiv.org/abs/2601.02991 · HTML: https://mlsanity.com/paper/2601.02991/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 18 of 18)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output](https://mlsanity.com/paper/2407.03320/) (2024)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [Ovis: Structural Embedding Alignment for Multimodal Large Language Model](https://mlsanity.com/paper/2405.20797/) (2024)
- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training](https://mlsanity.com/paper/2410.08202/) (2024)
- [Unlocking Multimodal Mathematical Reasoning via Process Reward Model](https://mlsanity.com/paper/2501.04686/) (2025)
- [When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?](https://mlsanity.com/paper/2503.23137/) (2025)
- [Let Androids Dream of Electric Sheep: A Human-Inspired Image Implication Understanding and Reasoning Framework](https://mlsanity.com/paper/2505.17019/) (2025)
- [Multimodal Mathematical Reasoning with Diverse Solving Perspective](https://mlsanity.com/paper/2507.02804/) (2025)

## Abstract (arXiv)

Comic understanding presents a significant challenge for Multimodal Large Language Models (MLLMs), as the intended meaning of a comic often emerges from the joint interpretation of visual, textual, and social cues. This naturally motivates Chain-of-Thought (CoT) prompting, since explicit intermediate reasoning appears promising for integrating such heterogeneous signals. However, existing CoT methods are poorly matched to this structure: they tend to force interpretation into a single reasoning path before multiple cues have been jointly considered, often degrading performance, especially for small MLLMs. Our key idea is to explicitly preserve multi-cue interpretation during supervision construction, rather than collapsing comic understanding into a single reasoning chain. To this end, we propose a two-stage framework for faithful comic reasoning in small MLLMs. First, we introduce MoCoT, a modular supervision construction framework that preserves multi-cue interpretation and turns it into more faithful supervision. Second, we propose VERA, a structured reward mechanism that turns such supervision into faithful reasoning behavior by aligning optimization with both reasoning faithfulness and answer correctness. Extensive experiments on five benchmarks spanning comic understanding and broader humor-centric and abstract visual reasoning tasks demonstrate that our framework achieves strong results in the ≤ 4B regime, surpasses several 7B baselines, improves four small MLLMs by an average of 12.1% as a plug-in, and consistently enhances reasoning faithfulness while preserving inference efficiency.