AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

SGoT-R1: Social Graph of Thought Reasoning-Enhanced Multimodal Large Language Model for Harmful Meme Detection

Xiuxian Wang, Yuting Su, Wenhui Li, Xiaowen Wang, Zhuojun Li, Anan Liu

AAAI 2026 · Large language models › Reasoning and chain of thought · approach: Search and self-correction in reasoning · 0 citations (OpenAlex)

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 SGoT-R1, a reasoning-enhanced multimodal LLM for harmful meme detection that builds on social graph-of-thought style reasoning (abstract truncated; details beyond the abstract are not available).

Problem

Harmful meme detection requires understanding metaphorical multimodal content; prior LLM-reasoning-based methods reason only over the meme itself, without considering broader social context.

Approach

Extends reasoning for harmful meme detection beyond the meme content to social context via a social graph of thought, as suggested by the title; full method details unavailable from the truncated abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SGoT as input in zero-shot inference (ablation)GPT-4o · FHMaccuracy: 68.8 -> 72.1Improved
add SGoT as input in zero-shot inference (ablation)GPT-4o · Harm-Paccuracy: 63.1 -> 80.6Improved
add SGoT as input in zero-shot inference (ablation)Gemini 1.5 Flash · FHMaccuracy: 60.2 -> 67.8Improved
add SGoT as input in zero-shot inference (ablation)Gemini 1.5 Flash · Harm-Paccuracy: 61.6 -> 78.2Improved
add SGoT as input in zero-shot inference (ablation)GPT-4o · Harm-Caccuracy: 67.5 -> 73.2Improved
distill SGoT reasoning into the model instead of generating SGoT with base model at inference (ablation)GPT-4o w/ SGoT vs SGoT-R1-7B · FHMinference time: 15.3s -> 1.62sImproved
add SGoTRE training instead of plain SFT (ablation)Qwen2VL-7B · FHMaccuracy: 78.6 -> 84.5Improved
add SGoTRE training instead of plain SFT (ablation)Qwen2VL-2B · FHMaccuracy: 76.2 -> 79.4Improved
add SGoTRE training instead of plain SFT (ablation)Qwen2VL-2B · Harm-Paccuracy: 80.3 -> 89.0Improved
add SGoTRE training instead of plain SFT (ablation)Qwen2VL-7B · Harm-Caccuracy: 85.9 -> 89.0Improved
add SFT to zero-shot Qwen2VL-7B (ablation)Qwen2VL-7B · FHMaccuracy: 63.8 -> 78.6Improved
scale SGoT-R1 from 2B to 7BSGoT-R1 · FHMaccuracy: 79.4 -> 84.5Improved

Limitations

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