人工创业认知：在大语言模型（LLMs）内部定位并因果操控机会识别旋钮
Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)
浏览论文内容
中文总结 AI 辅助
本研究提出人工创业认知概念，通过表征工程在LLM内部定位机会识别方向并因果操控，首次实现对创业构念内部表征的干预，为创业研究开辟新对象。
中文摘要 AI 辅助
创业认知是创业研究的基础。然而，大语言模型（LLMs）越来越多地参与创业工作，将认知问题从人类行为者扩展到其内部表征在很大程度上尚未被探索的系统。我们引入了人工创业认知，即人工智能（AI）系统内部与创业相关的表征和计算的功能组织。我们通过表征工程将机制可解释性引入创业研究。聚焦于机会识别（OR），我们构建了636对匹配的OR存在与OR缺失情景对，并在Llama 3.1 8B-Instruct中恢复了OR方向。我们不是从输出中推断该构念，而是直接干预这一方向，沿着我们称之为机会识别旋钮的方向上下引导模型，其机会判断随之改变。据我们所知，这是首次对LLM内部创业构念的内部表征进行因果干预。保留测试、词汇和主题控制、行为消融以及几何比较表明，该方向是可恢复的、具有因果效应的，并且与机会评估和开发方向不同，尽管引导它也会改变对这些相邻阶段的判断。恢复、有符号引导和几何分离在跨越不同规模和系列的四个额外LLM中保持一致。这些结果为机会识别与评估之间存在争议的区分在AI系统内部提供了具体的表征形式。更广泛地说，它们将内部表征确立为创业研究的新对象，并展示了创业理论如何指导其识别、因果操控和解释。
英文摘要
Entrepreneurial cognition is a foundation of entrepreneurship research. Yet the growing involvement of large language models (LLMs) in entrepreneurial work extends the cognition question beyond human actors to systems whose internal representations remain largely unexplored. We introduce artificial entrepreneurial cognition, the functional organisation of entrepreneurship-relevant representations and computations inside artificial intelligence (AI) systems. We bring mechanistic interpretability into entrepreneurship research through representation engineering. Focusing on opportunity recognition (OR), we construct 636 matched OR-present and OR-absent scenario pairs and recover an OR direction in Llama 3.1 8B-Instruct. Rather than infer the construct from outputs, we intervene directly on this direction, steering the model up and down along what we call the opportunity recognition dial, and its opportunity judgments shift with it. To our knowledge, this is the first causal intervention on an internal representation of an entrepreneurship construct inside an LLM. Held-out tests, lexical and topical controls, behavioural ablation, and geometric comparisons show that the direction is recoverable, consequential, and distinct from the opportunity evaluation and exploitation directions, although steering it also shifts judgments about these neighbouring stages. Recovery, signed steering, and geometric separation hold across four additional LLMs spanning different scales and families. These results give the contested distinction between opportunity recognition and evaluation a concrete representational form inside AI systems. More broadly, they establish internal representations as a new object of entrepreneurship inquiry and show how entrepreneurship theory can guide their identification, causal manipulation, and interpretation.
发表机构
- Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学跨学科安全、可靠性与信任中心（SnT））
- Amsterdam Business School, University of Amsterdam（阿姆斯特丹大学阿姆斯特丹商学院）
- Stanford Graduate School of Business, Stanford University（斯坦福大学斯坦福商学院）
机构由 AI 辅助整理，请以论文原文为准。
