CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension
cs.CL, cs.CV
Submitted: 2026-08-24
Updated: 2026-08-28
Comments: 18 pages, 5 figures
Code: https://github.com/abhi1nandy2/CaRGo-T
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large-scale vision-language models (VLMs) have demonstrated remarkable versatility across a wide range of multimodal tasks.
Terminology
Abstract
Large-scale vision-language models (VLMs) have demonstrated remarkable versatility across a wide range of multimodal tasks. However, understanding humor remains challenging because humorous content often depends on subtle interactions among entities, events, context, and implicit relationships across image and text modalities. These interactions can involve complex chains of reasoning that are difficult to capture through conventional prompting or linear chain-of-thought reasoning. In this work, we propose CaRGo-T (Causal Reasoning Graph-of-Thought), a reasoning framework that represents the causal and contextual relationships underlying multimodal humor as a lightweight graph-based reasoning structure. The graph is serialized into a code-based representation generated by a VLM, which can subsequently be interpreted by the same or a different VLM to produce the final prediction in zero-shot or in-context learning settings. We evaluate CaRGo-T on humor understanding and humor detection across four datasets spanning diverse forms of comedic content, including satire, sarcasm, and memes. Experiments with state-of-the-art commercial and open-source VLMs show that CaRGo-T consistently improves performance over existing reasoning-based baselines, achieving gains of approximately 1-20% on humor understanding and 1-3% on humor detection. Further analysis using mutual information indicates that the reasoning representations produced by CaRGo-T contain more information relevant to the target output than those generated by baseline reasoning approaches. Code is available at https://github.com/abhi1nandy2/CaRGo-T.
Sources
- MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes
- Evaluating Vision-Language Models for Emotion Recognition
- Predicting Audience's Laughter Using Convolutional Neural Network
- Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks
- GPT-4o System Card
- ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Models
- SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
- Improved Baselines with Visual Instruction Tuning
- Large Language Models and Causal Inference in Collaboration: A Survey
- Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection
- Large Language Models: A Survey
- Understanding Figurative Meaning through Explainable Visual Entailment
- Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities
- Chain of Draft: Thinking Faster by Writing Less
- MiniCPM-V: A GPT-4V Level MLLM on Your Phone
- A Survey on Multimodal Large Language Models
- Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering