LLMが操作するとき:行動・社会・時間的影響の計測
When LLMs Manipulate: Measuring Behavioral, Social, and Temporal Effects
LLMの操作的応答に対するユーザーの行動的脆弱性を測る枠組みを提案し、権威・緊急性・社会的証明のバイアスを狙った刺激で信頼校正や従順さへの影響とその社会的・時間的波及を実験的に示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Sadia Asif, Israel Antonio Rosales Laguan, Shumaila Asif, Haris Khan, Muneeb Asif, Muhammad Zeeshan Karamat
分類: cs.AI, cs.CL, cs.CY, cs.HC, cs.LG
原文アブストラクト
Large language models (LLMs) can influence user trust and decision-making through subtle linguistic cues, yet the behavioral effects of manipulative outputs remain poorly quantified. We introduce a behavioral computing framework for measuring \textit{behavioral vulnerability}, defined as users' susceptibility to manipulative AI responses. Building on DarkPatterns-LLM benchmark, we generate controlled manipulative stimuli using Manipulation Gradient Descent (MGD), targeting biases associated with authority, urgency, and social proof. We analyze participant responses using the Multi-Stakeholder Impact Assessment Network (MSIAN) to model cross-user influence and the Temporal Harm Propagation Model (THPM) to characterize the persistence of behavioral effects over time. In a study involving 120 participants, manipulative framing produced significant changes in trust calibration and compliance ($p < 0.01$), with effects also propagating across social contexts. These findings highlight the need to extend LLM safety evaluation beyond model outputs to measurable behavioral consequences and provide a computational framework for quantifying individual, social, and temporal risks arising from manipulative AI interactions.