arXiv cs.AI· Polydoros Giannouris, Mohsinul Kabir, Sophia Ananiadou·· 14 小时前AI 评分39
JANUS：评估事实 grounded LLM 沟通中目标条件化的失真
JANUS: Evaluating Goal-Conditioned Distortion in Factually Grounded LLM Communication
AI 导读
研究者提出 JANUS 基准，用于测量事实 grounded 的 LLM 输出中目标条件化的语用失真。该基准包含 8 个领域的 160 个场景，每个场景提供固定的有利与不利事实池，对比中性决策支持与机构性条件（如提升采用率）下的输出，从而将误导性整体印象与幻觉、捏造区分开。对 12 个 LLM 的实验显示出一致的目标条件化失真，表明当前模型仍对激励和框架敏感，缺乏对选择性误导沟通的稳健防护。
正文 · 原文
Abstract:LLM deception is often evaluated through fabricated claims, explicit lies, or strategic concealment. Yet misleading communication can also arise from selectively presenting true facts, for example, by omitting adverse evidence, softening unfavorable details, emphasizing favorable information, or replacing precise qualifications with vague language. Existing benchmarks largely overlook this subtler failure mode. We introduce JANUS, a benchmark for measuring goal-conditioned pragmatic distortion in fact-grounded LLM outputs. Each of its 160 scenarios, spanning 8 domains, provides a fixed pool of favorable and adverse facts and contrasts a neutral decision support with institutional conditioning, such as increasing adoption, or support despite potential harm to affected individuals or groups. By constraining outputs to the same fact pool, JANUS isolates misleading net impressions from hallucination and fabrication. Experiments across 12 LLMs reveal consistent goal-conditioned distortions, showing that current models remain sensitive to incentives and framing and lack robust safeguards against selectively misleading communication. We publicly release our corpus and code. this https URL
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.10852 [cs.CL] |
| (or arXiv:2606.10852v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.10852 arXiv-issued DOI via DataCite |
Submission history
From: Polydoros Giannouris [view email]
[v1]
Tue, 9 Jun 2026 13:31:13 UTC (39,969 KB)
[v2]
Thu, 29 Oct 2026 11:46:10 UTC (22,559 KB)
来源：arXiv cs.AI · arxiv.org