arXiv cs.CL· Abdelkader Metales, Miriam Grabenheinrich, Aicha Metales·· 11 小时前AI 评分49
副本不等于确认：新闻重复如何误导 LLM 评判器与持续学习器
Copies Are Not Confirmations: How News Duplication Fools LLM Judges and Continual Learners
AI 导读
在 20 万篇英文 CC-News 文章中，MinHash 检测器发现 18.9% 存在另一媒体的近重复副本，能关联 92% 的编辑转载，却无法识别 phi4、Llama 3.2 或 Gemini 2.5 Flash 的改写。
正文 · 原文
Abstract:Many news reports of a claim are copies of one source: wire stories, content shared within a media group, syndicated features and press releases. We ask whether LLM judges and continual learners treat such copies as independent confirmations. In 200,000 English CC-News articles, a MinHash detector links 18.9% to a near-copy from another outlet (precision 0.97 once boilerplate is removed); it links 92% of edited reprints to their originals but none of the LLM rewrites by phi4, Llama 3.2 or Gemini 2.5 Flash. Shown three identical reprints of a claim about an unknown person instead of one report, Llama 3.2 3B and phi4 14B raised the share of lies they accepted from 0.06 to 0.71 and from 0.21 to 0.90 and ignored a note that the reports came from one source; Gemini 2.5 Flash already believed a single report, and Gemini 2.5 Pro followed provenance notes and tables. In a simulated continual-learning stream, showing the judge one report per detected chain cut the copied lies it accepted by 0.10-0.24 across four judges, at a mean cost of no more than 4.2 percentage points of accepted truths. Against reworded copies, a test of how many of a report's named entities are absent from an earlier look-alike separates LLM rewrites from 100 labelled independent reports of the same event with AUC 0.98-0.99 and wrongly flags one; entity overlap alone does as well, TF-IDF and a current embedding model come close, and the test catches few natural same-source derivatives. With the miss patterns of generated rewrite networks, it cut the reworded-copy lies accepted from 0.67 to 0.20 (0.40 when the rewriter invents details). Counting reports or chains alone is not a reliable defence, the effect of provenance information depends on the judge, and colluding sources remain the open problem. Code and labels: this https URL
| Comments: | 19 pages, 13 tables. Code, labels and results: this https URL |
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL) |
| ACM classes: | I.2.7; I.2.6 |
| Cite as: | arXiv:2611.09203 [cs.LG] |
| (or arXiv:2611.09203v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.09203 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Abdelkader Metales [view email]
[v1]
Fri, 6 Nov 2026 09:22:29 UTC (25 KB)
来源：arXiv cs.CL · arxiv.org