arXiv · cs.AI · Mosab Alfaqeeh, Omar Mohammed Horani, Mou'th Hourani, Hashem Alfaqeeh · 10 小时前模型评分53
研究：人工智能（AI，Artificial Intelligence） 研究智能体论文中的数字多为来源错配而非编造
Beyond fabrication: Misattributed numbers in papers written by AI research agents
导读
一项 arXiv 论文重新分析了某公开 人工智能（AI，Artificial Intelligence） 研究智能体基准的全部 540 条已发布判定，并人工标注 18 份提交中的 256 条数字主张，发现失败集中在论文与底层工作之间的对应关系，而非公然造假。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：ai-tooling，需要人工复核。
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
应用领域：科学研究
事件类型：研究发布
证据摘录
- “We introduce a deterministic claim-to-evidence checker that scores whether the surrounding context identifies the claimed result and calibrates each claim against numerical decoys.”
- “With its rules fixed before labeling, it certifies claims with over 90% precision against blinded annotators (78 of 85; Cohen's kappa = 0.89), while verifying only a subset of claims; most claims it cannot verify are nevertheless traceable, so failure to verify is not evidence of falsehood.”
- “An LLM verifier given the same evidence recovers more traceable claims but accepts about three times as many misattributed ones, so the two are best used together.”
来源：arXiv · cs.AI · arxiv.org