arXiv cs.CL· Hasan Amin, Zhuoran Lu, Ming Yin·· 3 天前AI 评分36
似然不等于作者身份：AI 辅助写作中的人类贡献能否被可靠度量？
Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing?
AI 导读
一项 arXiv 研究指出，基于提示词对文本预测能力的“人类贡献”度量可被轻易操纵：只需让模型从提示词中复制几个随机 ID（SPECIFICITY PADDING），仅给标题的请求就会显得比提供核心思想的请求更“像人写的”。
正文 · 原文
Abstract:AI-text detection generally asks whether a machine wrote a text. As AI becomes an increasingly integral and accepted part of writing, the more relevant question is no longer whether AI was used, but how much of the text reflects human contribution. A prominent line of work estimates this by measuring how predictive a person's prompt is of the final text. We show that this measure can be easily manipulated. We introduce SPECIFICITY PADDING that simply asks the model to copy a few random IDs from the prompt, and that alone makes a title-only request look more human than one that supplies the article's key ideas. A context-swap audit then holds each document fixed, and only shows or hides the IDs to the evaluator. The score of the unchanged text swings by a third to half of its scale, and it rises for every document we test, on news and scientific abstracts, across varied LLMs from 3.8B to 753B parameters. The same articles can average 85\% human or 15\% human depending only on which prompt is on record, and even with no prompt at all, the output-only variant rewards the random strings themselves. An exact identity, the credit ledger, explains why. The score is a surprisal-weighted average over the text, so rare strings that the context makes copyable collect the credit, whatever they mean. A two-point bound marks a deeper limit. If the prompt could have been machine-written, every transcript-only method must, in the worst case, miss by half the contribution at stake. Likelihood-based scores alone cannot reliably establish human contribution without evidence of what the person added and how the text was produced.
| Subjects: | Computation and Language (cs.CL) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2610.19767 [cs.CL] |
| (or arXiv:2610.19767v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19767 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhuoran Lu [view email]
[v1]
Wed, 14 Oct 2026 08:18:02 UTC (326 KB)
来源：arXiv cs.CL · arxiv.org