跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2603.27928 · v2

Generalizable Social Bot Detection via Multi-Granularity Summarization and Domain-Invariant Learning

首次提交 2026-03-30 08:52
版本更新 2026-11-16 12:44
雷达观测 2026-11-17 17:12
arXiv ↗PDF ↗

摘要

Social bots are becoming increasingly sophisticated in mimicking human users, posing persistent threats to online information ecosystems. Despite substantial progress in social bot detection, existing methods often generalize poorly to unseen datasets. Two challenges underlie this limitation: heterogeneous user information across datasets makes consistent representation difficult, while distribution shifts encourage reliance on domain-specific patterns. To address these challenges, we propose Multi-Granularity Summarization and Domain-Invariant Learning (MGDIL), a unified framework for generalizable social bot detection. MGDIL first converts profile attributes into structured textual descriptions and summarizes historical posts into user-level behavioral representations, providing a shared semantic interface across heterogeneous datasets. It then combines task-oriented instruction tuning, domain-adversarial learning, and cross-domain contrastive learning to reduce dependence on domain-specific patterns while preserving discriminative information between bots and human users. We construct a unified instruction-tuning corpus from 15 social bot datasets, train MGDIL on 13 earlier datasets, and evaluate it on two later-collected unseen datasets under a temporally ordered cross-dataset protocol. Comparisons with representative conventional, neural, LLM-based, and transfer-based baselines, together with ablation and representation analyses, demonstrate the effectiveness of MGDIL in improving generalization across datasets. The code is available at: https://github.com/QQQQQQBY/MGDIL.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-16 12:44 · 最新观测版本

Generalizable Social Bot Detection via Multi-Granularity Summarization and Domain-Invariant Learning

Social bots are becoming increasingly sophisticated in mimicking human users, posing persistent threats to online information ecosystems. Despite substantial progress in social bot detection, existing methods often generalize poorly to unseen datasets. Two challenges underlie this limitation: heterogeneous user information across datasets makes consistent representation difficult, while distribution shifts encourage reliance on domain-specific patterns. To address these challenges, we propose Multi-Granularity Summarization and Domain-Invariant Learning (MGDIL), a unified framework for generalizable social bot detection. MGDIL first converts profile attributes into structured textual descriptions and summarizes historical posts into user-level behavioral representations, providing a shared semantic interface across heterogeneous datasets. It then combines task-oriented instruction tuning, domain-adversarial learning, and cross-domain contrastive learning to reduce dependence on domain-specific patterns while preserving discriminative information between bots and human users. We construct a unified instruction-tuning corpus from 15 social bot datasets, train MGDIL on 13 earlier datasets, and evaluate it on two later-collected unseen datasets under a temporally ordered cross-dataset protocol. Comparisons with representative conventional, neural, LLM-based, and transfer-based baselines, together with ablation and representation analyses, demonstrate the effectiveness of MGDIL in improving generalization across datasets. The code is available at: https://github.com/QQQQQQBY/MGDIL.

查看此版本解读 →查看此版本原文 ↗