Research

Paper

AI LLM March 12, 2026

Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks

Authors

Mei Chee Leong, Ying Gu, Hui Li Tan, Liyuan Li, Nancy Chen

Abstract

Frontier Multimodal Large Language Models (MLLMs) exhibit remarkable capabilities in Visual-Language Comprehension (VLC) tasks. However, they are often deployed as zero-shot solution to new tasks in a black-box manner. Validating and understanding the behavior of these models become important for application to new task. We propose an Explicit Logic Channel, in parallel with the black-box model channel, to perform explicit logical reasoning for model validation, selection and enhancement. The frontier MLLM, encapsulating latent vision-language knowledge, can be considered as an Implicit Logic Channel. The proposed Explicit Logic Channel, mimicking human logical reasoning, incorporates a LLM, a VFM, and logical reasoning with probabilistic inference for factual, counterfactual, and relational reasoning over the explicit visual evidence. A Consistency Rate (CR) is proposed for cross-channel validation and model selection, even without ground-truth annotations. Additionally, cross-channel integration further improves performance in zero-shot tasks over MLLMs, grounded with explicit visual evidence to enhance trustworthiness. Comprehensive experiments conducted for two representative VLC tasks, i.e., MC-VQA and HC-REC, on three challenging benchmarks, with 11 recent open-source MLLMs from 4 frontier families. Our systematic evaluations demonstrate the effectiveness of proposed ELC and CR for model validation, selection and improvement on MLLMs with enhanced explainability and trustworthiness.

Metadata

arXiv ID: 2603.11689
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-12
Fetched: 2026-03-14 05:03

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11689v1</id>\n    <title>Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks</title>\n    <updated>2026-03-12T08:56:14Z</updated>\n    <link href='https://arxiv.org/abs/2603.11689v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11689v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Frontier Multimodal Large Language Models (MLLMs) exhibit remarkable capabilities in Visual-Language Comprehension (VLC) tasks. However, they are often deployed as zero-shot solution to new tasks in a black-box manner. Validating and understanding the behavior of these models become important for application to new task. We propose an Explicit Logic Channel, in parallel with the black-box model channel, to perform explicit logical reasoning for model validation, selection and enhancement. The frontier MLLM, encapsulating latent vision-language knowledge, can be considered as an Implicit Logic Channel. The proposed Explicit Logic Channel, mimicking human logical reasoning, incorporates a LLM, a VFM, and logical reasoning with probabilistic inference for factual, counterfactual, and relational reasoning over the explicit visual evidence. A Consistency Rate (CR) is proposed for cross-channel validation and model selection, even without ground-truth annotations. Additionally, cross-channel integration further improves performance in zero-shot tasks over MLLMs, grounded with explicit visual evidence to enhance trustworthiness. Comprehensive experiments conducted for two representative VLC tasks, i.e., MC-VQA and HC-REC, on three challenging benchmarks, with 11 recent open-source MLLMs from 4 frontier families. Our systematic evaluations demonstrate the effectiveness of proposed ELC and CR for model validation, selection and improvement on MLLMs with enhanced explainability and trustworthiness.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-12T08:56:14Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Mei Chee Leong</name>\n    </author>\n    <author>\n      <name>Ying Gu</name>\n    </author>\n    <author>\n      <name>Hui Li Tan</name>\n    </author>\n    <author>\n      <name>Liyuan Li</name>\n    </author>\n    <author>\n      <name>Nancy Chen</name>\n    </author>\n  </entry>"
}