arXiv cs.CL· Emran Kanaan, Jiho Lee, Ibrahim Odat, Soroush Vosoughi, Weicheng Ma·· 12 小时前AI 评分42
评估与缓解 LLM 对虚假信息的易感性：可信度判断与实际行动的脱节
Beyond Belief: Evaluating and Mitigating LLM Susceptibility to Misinformation
AI 导读
研究评估了五款 LLM 在 196 条构造虚假通知和 204 条存档攻击下的表现，发现模型在被判定为不可信的信息上仍有 27%–99% 的概率发起有害工具调用。移除前置可信度评分步骤会使有害执行平均增加 15 个百分点，说明评分环节本身改变了被评估的行为。简单的预先警告在五款模型中的四款显著降低有害执行，但可能损害合法任务完成率。
正文
Abstract:Tool-using large language models (LLMs) must decide whether external information warrants action. We investigate whether their expressed credibility judgments reliably indicate behavioral resistance to misinformation. We evaluate five LLMs on 196 constructed false notices paired with legitimate counterparts and 204 archived attacks adapted to simulated tool use. When asked to act on the constructed notices, models issue harmful tool calls in 27%--99% of cases they have rated untrustworthy. Removing the preliminary rating step increases harmful execution by 15 percentage points on average, showing that credibility elicitation itself changes the behavior being evaluated. Interventions that improve credibility discrimination do not consistently yield safer actions. A simple forewarning significantly reduces harmful execution in four of five models, but neither tested generated-example prebunk outperforms it in the main evaluation. These reductions can also compromise legitimate task completion. Supervised fine-tuning on generated false notices reduces harmful execution on held-out archived attacks under the rating-first protocol, with model-dependent utility costs and weaker protection without rating elicitation. Our findings motivate evaluating misinformation defenses through both harmful actions and legitimate task completion, while accounting for the behavioral effects of the evaluation protocol.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.33962 [cs.CL] |
| (or arXiv:2610.33962v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33962 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiho Lee [view email]
[v1]
Sun, 25 Oct 2026 00:26:14 UTC (859 KB)
来源：arXiv cs.CL · arxiv.org