# Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks Source: [Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks]() Collection index: [llms.txt]() Data updated: 2026-07-03T05:00:04.966Z Authors: Mei Chee Leong, Ying Gu, Hui Li Tan, Liyuan Li, Nancy Chen Published: 2026-03-12T08:56:14.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Human-Centric Referring Expression Comprehension (HC-REC) on HC-RefLoCo (val)](): Human-Centric Referring Expression Comprehension (HC-REC); HC-RefLoCo (val); Acc@0.50: not recorded. - [Human-Centric Referring Expression Comprehension (HC-REC) on HC-RefLoCo (test)](): Human-Centric Referring Expression Comprehension (HC-REC); HC-RefLoCo (test); Accuracy@0.5: not recorded. - [Multiple Choice Visual Question Answering on NegBench COCO (test)](): Multiple-choice Visual Question Answering; NegBench COCO (test); Accuracy: not recorded. - [Multiple Choice Visual Question Answering on NegBench VOC 2007 (test)](): Multiple-choice Visual Question Answering; NegBench VOC 2007 (test); Accuracy: not recorded. - [Referring Expression Comprehension on HC-RefCOCOg (val)](): Referring Expression Comprehension; HC-RefCOCOg (val); Acc@0.50: not recorded. - [Referring Expression Comprehension on HC-RefCOCOg (test)](): Referring Expression Comprehension; HC-RefCOCOg (test); Acc@0.50: not recorded. ## Original sources and implementation [Original paper]() [PDF]()