arXiv cs.AI· Zhiwei Xu, Xuyang Liu, Xiaolin Peng, Weixian Deng, Jiabao Gao, Zirui Li, Tian Qiu, Boya Zhou, Wei Jiao, Hai Wan, Xibin Zhao·· 14 小时前AI 评分31
TrustJev：将策略权限与不可信证据分离的 LLM 决策框架
TrustJev: Separating Policy Authority from Untrusted Evidence in LLM-Based Decisions
AI 导读
TrustJev 框架通过受保护策略评分与有界证据修正，将策略权限与不可信证据分离，防止外部证据中的指令覆盖应用策略。0.6B 实现在三个数据集上取得最高平均 Balance，较最强基线高 0.57-1.05 个百分点；授权基准中 95.77% 的来源能正确应对全部 32 个攻击，对比基线为 80.98%。推理内存与中位延迟相当，额外开销主要在训练阶段。
正文 · 原文
Authors:Zhiwei Xu, Xuyang Liu, Xiaolin Peng, Weixian Deng, Jiabao Gao, Zirui Li, Tian Qiu, Boya Zhou, Wei Jiao, Hai Wan, Xibin Zhao
Abstract:Decision models enable software to select from predefined actions using natural language inputs. However, the external evidence that supplies facts for these decisions may also contain instructions that attempt to override the application's policy. We propose TrustJev, a framework combining protected policy scoring with bounded evidence corrections. A single Transformer backbone computes policy scores and a correction budget from trusted policy and candidates, then bounds evidence corrections by that budget. Paired supervision encourages stable predictions under instruction insertions that preserve task facts and changed preferences when edits change the correct answer. Authority supervision accommodates evidence when the policy alone cannot determine the decision. We evaluate a 0.6B implementation against 14 baselines on three datasets covering authentication, instruction hierarchy, and executable authorization rules. TrustJev achieves the highest mean Balance, the harmonic mean of accuracy on non-attack and attack inputs, exceeding the strongest baseline on each by 0.57-1.05 percentage points. In the authorization benchmark, it correctly answers all 32 attacks per source in a fixed pool for 95.77% of sources, compared with 80.98% for the strongest comparator. TrustJev maintains comparable inference memory and median latency, with additional overhead primarily during training.
| Comments: | 12 pages |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.34826 [cs.AI] |
| (or arXiv:2610.34826v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34826 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhiwei Xu [view email]
[v1]
Mon, 26 Oct 2026 04:17:53 UTC (930 KB)
来源：arXiv cs.AI · arxiv.org