arXiv：cs.CL· Kanay Gupta, David Y. Liu, Aditya Joshi·· 11 小时前
用不可靠叙述者框架为澳大利亚与美国讽刺新闻生成低成本解释
Unreliable Narrator Framing as a Cost-effective Mechanism for Satire Explanation of Australian and American Satirical News
AI 导读
一项试点研究比较了澳大利亚与美国讽刺新闻的解释生成，发现基于不可靠叙述者理论、在开放权重模型上构建解释，可作为前沿模型的可行且低成本替代方案。模型在美国来源上识别讽刺修辞手法的准确率高于澳大利亚来源。该工作产出了一个新数据集和讽刺解释评测基准。
正文
Abstract:Satirical news is a unique form of misinformation: it is intended to be humorous by the original publication source but can be misinterpreted. Explanation of satirical news articles is challenging because recent and local context needs to be incorporated. This is a pilot study that explores explanation generation for satirical news articles from Australia and compares them alongside those from USA. The paper demonstrates that framing explanations on unreliable narrator theory on open-weights models can be a feasible, cost-effective alternative to frontier models. We find that models identify the satirical tropes more accurately on the American source than the Australian one. This work results in a novel dataset and an evaluation benchmark for satirical explanation.
| Comments: | 4 content pages + references, appendix; ACL Stylesheet; Under review |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.12863 [cs.CL] |
| (or arXiv:2610.12863v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12863 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aditya Joshi [view email]
[v1]
Fri, 9 Oct 2026 01:41:47 UTC (37 KB)
来源：arXiv：cs.CL · arxiv.org