按年被提到
20242024 · 6 次2026
AI 安全、伦理与社会影响›大模型与人类行为·arXiv:2404.01332 · cs.CL

Explaining Large Language Models Decisions Using Shapley Values

Behnam Mohammadi · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-04-03 · 最近 2024-12-28
2不同的人
5活跃月份
6讨论串
10被引(OpenAlex)
arXiv 摘要(候选层不写导读)

The emergence of large language models (LLMs) has opened up exciting possibilities for simulating human behavior and cognitive processes, with potential applications in various domains, including marketing research and consumer behavior analysis. However, the validity of utilizing LLMs as stand-ins for human subjects remains uncertain due to glaring divergences that suggest fundamentally different underlying processes at play and the sensitivity of LLM responses to prompt variations. This paper presents a novel approach based on Shapley values from cooperative game theory to interpret LLM behavior and quantify the relative contribution of each prompt component to the model's output. Through two applications - a discrete choice experiment and an investigation of cognitive biases - we demonstrate how the Shapley value method can uncover what we term "token noise" effects, a phenomenon where LLM decisions are disproportionately influenced by tokens providing minimal informative content. This phenomenon raises concerns about the robustness and generalizability of insights obtained from LLMs in the context of human behavior simulation. Our model-agnostic approach extends its utility to proprietary LLMs, providing a valuable tool for practitioners and researchers to strategically optimize prompts and mitigate apparent cognitive biases. Our findings underscore the need for a more nuanced understanding of the factors driving LLM responses before relying on them as substitutes for human subjects in survey settings. We emphasize the importance of researchers reporting results conditioned on specific prompt templates and exercising caution when drawing parallels between human behavior and LLMs.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论behnamoh · 2024-05

“Whenever "AI influencers" say "prompt engineering is dead", I realize they are full of bs. If anything, prompt engineering has become more nuanced, down to the choice of each token: https://arxiv.org/abs/2404.01332”

A web version of Anthropic's prompt engineering interactive tutorial原评论 ↗
被提交为 story · 5 次