AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

CLER: Improving Multimodal Financial Reasoning by Cross-MLLM Error Reflection

Shuangyan Deng, Zhongsheng Wang, Rui Mao, Ciprian Doru Giurcăneanu, Jiamou Liu

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes CLER, a cross-MLLM error reflection method that improves multimodal financial reasoning by using errors from stronger models to guide a smaller MLLM, aiming to cut inference costs.

Problem

MLLMs struggle with financial terminology, logical consistency, and numerical computation over joint text-image financial inputs, while commercial models that do well are too expensive for scalable financial use.

Approach

Uses cross-model error reflection: errors made by MLLMs are reflected upon to improve reasoning, with the goal of transferring stronger-model capability to a cheaper model. Details are not available beyond the abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add cross-model error retrieval and reflection (CLER) over plain CoTGPT-4o · FinMR (all)accuracy (%): 54.17 -> 61.18Improved
add reflection on retrieved error pairs (ablation)CLER (GPT-4o) · FinMR (expertise)accuracy (%): 60.33 -> 65.90Improved
use contrastive retriever instead of semantic-similarity retriever (ablation)CLER (GPT-4o) · FinMR (all)accuracy (%): 58.52 -> 61.18Improved
use contrastive retriever instead of semantic-similarity retriever (ablation)CLER (GPT-4o) · MMMU-Finance (math)accuracy (%): 63.00 -> 66.78Improved
add retrieval without reflection over CoT (ablation)GPT-4o · MMMU-Finance (math)accuracy (%): 62.77 -> 62.99No clear effect
apply LEAP principles instead of CoTGPT-4o · FinMR (math)accuracy (%): 49.40 -> 42.97Hurt
apply LEAP principles instead of CoTGPT-4o · FAMMA (all)accuracy (%): 54.50 -> 54.50No clear effect
apply LEAP principles instead of CoTClaude-4-sonnet · FAMMA (math)accuracy (%): 59.00 -> 57.00Hurt
generate insights individually at test time instead of general pre-generated principles (ablation)CLER · FinMRaccuracy (%): +3.0% for GPT-4oImproved
reduce error database size to 80% and 50% (ablation)CLER · FinMR, FAMMA, MMMU-FinanceaccuracyHurt
upgrade backbone from Claude-3.7-sonnet to Claude-4-sonnet under CLER (ablation)CLER · FinMR (all)accuracy (%): 62.85 -> 65.10Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy