arXiv cs.CL· Aisvarya Adeseye, Adeyemi Adeseye, Mohammad Tahir, Jouni Isoaho·· 2 天前AI 评分22
CARE-SD：面向文本数据本地 SLM 自我披露分析的可解释推理架构
CARE-SD: Explainable Reasoning Architecture for Local SLM Self-Disclosure Analysis in Textual Data
AI 导读
研究提出 CARE-SD 四模块架构，用于本地小语言模型的自我披露分析，在 82 份网络安全访谈上测试 Llama 1B、Qwen 1.5B 和 Llama 3B。该架构将 Llama 3B 的 Macro-F1 从 0.80 提升至 0.88，并将无依据论断减少 60%，3B 模型在类别 Macro-F1 上追平 20B 参考模型。
正文 · 原文
Abstract:Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical assessments. Consequently, identifying genuine self-disclosures is challenging because statements are context-dependent, categories overlap, and automated interpretations may introduce unsupported claims. Locally deployed Small Language Models (SLMs) protect sensitive participant data by keeping processing within controlled environments, but their limited reasoning capabilities make simple prompting insufficient for context-aware and factually reliable analysis. This study developed CARE-SD (Context-Adaptive Reasoning and Explanation for Self-Disclosure), a novel four-module architecture integrating context-adaptive processing, hierarchical disclosure reasoning, explanation-consistency verification, and cross-batch reconciliation. We evaluated three local SLMs, including Llama 1B, Qwen 1.5B, and Llama 3B, using 82 independently annotated cybersecurity interviews across five organizational sectors. Comparisons included conventional classifiers, three prompting strategies, larger 8B--32B models, and architectural ablations. Two independent reviewers assessed disclosure labels, factual claims, and explanation correctness. CARE-SD improved the accuracy and evidence reliability of SLMs, increasing Llama 3B Macro-F1 from 0.80 to 0.88 while reducing unsupported claims by 60\%. Remarkably, the 3B model matched the 20B reference model in category Macro-F1, demonstrating the effectiveness of the architecture without requiring a larger model.
| Comments: | Accepted for the 4th International Conference on Foundation and Large Language Models (FLLM2026) - IEEE - held from 17-20 Nov., 2026 at Novotel Barcelona City, Barcelona, Spain |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.21151 [cs.CR] |
| (or arXiv:2610.21151v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21151 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aisvarya Adeseye Mrs [view email]
[v1]
Thu, 15 Oct 2026 03:07:24 UTC (2,758 KB)
来源：arXiv cs.CL · arxiv.org