arXiv cs.AI· Zeba Afroz, Harsh Vardhan, Md. Shad Akhtar·· 3 天前AI 评分18
ReCoT：用标签引导的 CoT 优化做宣传检测推理
Reasoning for Propaganda Detection via Label-Guided CoT Optimisation
AI 导读
ReCoT 是一个推理条件化的宣传检测框架，通过群体级细化和性能引导重采样捕捉说服性技巧的定义性线索，无需额外解释标注。在 INDI-PROPspan 上其 macro F1_LCS 达 0.364，Avg F1_LCS 达到 SFT 上界的 88%；在 PTC 上 Avg F1_LCS 达到 SFT 上界的 85%，同时保持可解释性。对推理池收敛与更新模式的分析显示其推理 CoT 得到有效细化。
正文 · 原文
Abstract:Propaganda detection systems usually operate as black boxes, lacking explanations. To address this, we hypothesise that persuasive techniques contain definitional characteristics with respect to their social-political setting. We introduce ReCoT, a reasoning-conditioned detection framework that captures definitional cues of persuasive techniques via population-level refinement and performance-guided resampling, without requiring additional explanation annotations. On INDI-PROPspan, ReCoT achieves a macro F1_LCS of 0.364, surpassing baselines and reaching 88% of the SFT upper bound on Avg F1_LCS. Similarly, on PTC, ReCoT reaches 85% of the SFT upper bound on Avg F1_LCS, closing much of this gap while remaining interpretable. Importantly, the analysis of the reasoning pool's convergence and update pattern for ReCoT shows effective refinement of reasoning CoTs.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17271 [cs.AI] |
| (or arXiv:2610.17271v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17271 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zeba Afroz [view email]
[v1]
Mon, 12 Oct 2026 18:25:12 UTC (197 KB)
来源：arXiv cs.AI · arxiv.org