arXiv：cs.AI· Siddharth Bhargava, Sara Tonelli, Patricia Mart\'in-Rodilla·· 18 小时前
NARS：用神经符号论证推理检测 ChangeMyView 讨论中的说服力
Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions
AI 导读
研究者提出神经符号论证推理系统 NARS，直接从在线讨论中检测说服力，其神经部分用检索增强的迭代 LLM 推理抽取双极论证结构，符号部分用渐进论证语义传播论证影响。
正文
Abstract:Argument structures represent how individual arguments interact within a discourse. However, leveraging these structures to infer meaningful knowledge remains challenging, as it requires a formal representation of how argumentative influence propagates across the structure. We propose Neuro-symbolic Argumentation Reasoning System (NARS) for performing persuasiveness detection directly from online discussions. The neural component employs retrieval-augmented iterative LLM reasoning to extract bipolar argument structures, while the symbolic component applies gradual argumentation semantics to propagate argumentative influence over the structure.
Using the Webis-CMV-20 corpus, we construct CMV2BAS, a dataset of long, multi-threaded ChangeMyView discussions annotated with LLM-derived bipolar argument structures and labeled with delta events (view change vs.\ no change). We investigate whether gradual argumentation semantics can effectively detect persuasiveness, whether augmenting them with argument quality and graph-based centrality improves performance, and whether symbolic reasoning remains necessary in the presence of modern LLMs. NARS achieves F1=0.57 and AUC=0.56 under its best configuration, outperforming zero-shot Qwen3.6:27B and GPT-oss:20B. We identify support-dominant discussions and long argumentative chains as key failure modes limiting attack influence propagation. Our work demonstrates the feasibility of operationalizing formal gradual argumentation semantics over noisy real-world discourse for scalable macro-level persuasion analysis, while highlighting key challenges and directions for future research in neuro-symbolic argumentation reasoning. We release both CMV2BAS dataset and the NARS framework for public use.
| Comments: | Accepted and to be published in the Proceedings of the 25th International Conference on Knowledge Engineering and Knowledge Management (EKAW 2026) |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Symbolic Computation (cs.SC) |
| Cite as: | arXiv:2610.15091 [cs.CL] |
| (or arXiv:2610.15091v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15091 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Siddharth Bhargava [view email]
[v1]
Sat, 10 Oct 2026 18:00:05 UTC (973 KB)
来源：arXiv：cs.AI · arxiv.org