arXiv：cs.AI· Diego Revilla, Martin Fernandez-de-Retana, Lingfeng Chen, Aritz Bilbao-Jayo, Miguel Fernandez-de-Retana·· 5 小时前
用反事实图方法分析对立叙事：无需节点标注，PAN 基准 F1 达 0.93
A Counterfactual Graph Approach to Oppositional Narrative Analysis
AI 导读
研究者提出一种模块化框架，直接从叙事中抽取实体交互图并据此分类，不依赖人工标注的节点角色标签。该方法用领域适配的 BERT 编码器枚举候选实体，学习二部图结构后交由 Heterogeneous Graph Transformer 分类，并通过反事实蒸馏估计各节点的个体处理效应，平均剪除 75.2% 的图结构而不改变预测。
正文
Abstract:Distinguishing legitimate critical speech from coordinated conspiracy narratives is a pressing challenge for the integrity of the online information ecosystem, yet prevailing approaches rely on labeled entity roles and rigid predefined schemas that fail to capture the diffuse and context-dependent nature of participation in such narratives. We propose a modular framework that extracts an entity-interaction graph directly from narratives and reasons over it for classification, without depending on annotated node-level labels. Our pipeline enumerates candidate entity spans from a domain-adapted BERT encoder and learns a bipartite graph structure, which is then classified with a Heterogeneous Graph Transformer. To make predictions interpretable, we cast the graph as a hypergraph and apply a counterfactual distillation procedure that estimates the Individual Treatment Effect of each node, pruning extraneous entities to recover a minimal predictive subgraph. On the standard PAN Oppositional Narratives benchmark, our model achieves a macro F1-score of 0.93 and an MCC of 0.84, reaching state-of-the-art performance with roughly one-third of the parameters of the next best system, while pruning the graphs by 75.2% on average without altering predictions. Our results demonstrate that graph-based representations coupled with counterfactual inference offer both strong predictive accuracy and transparency into the entities driving conspiratorial discourse.
| Comments: | 14 pages, 2 figures. Accepted at the 40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: Trustworthy AI for Good (AI4GOOD) |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.06135 [cs.CL] |
| (or arXiv:2603.06135v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2603.06135 arXiv-issued DOI via DataCite |
Submission history
From: Miguel Fernandez-De-Retana [view email]
[v1]
Fri, 6 Mar 2026 10:41:58 UTC (378 KB)
[v2]
Tue, 10 Mar 2026 11:32:35 UTC (378 KB)
[v3]
Sun, 11 Oct 2026 10:57:06 UTC (518 KB)
来源：arXiv：cs.AI · arxiv.org