arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2407.02885cs.HCcs.CLcs.CYcs.SI
收藏

CogErgLLM：从认知工效学视角探索大语言模型系统设计

CogErgLLM: Exploring Large Language Model Systems Design Perspective Using Cognitive Ergonomics

Independent University（独立大学）；Shahjalal University of Science and Technology（沙赫贾拉勒科技大学）

Azmine Toushik Wasi, Mst Rafia Islam

备注：
10 Page, 3 Figures. Accepted in: (i) ICML'24: LLMs & Cognition Workshop (Non-archival; OpenReview: https://openreview.net/forum?id=63C9YSc77p) (ii) EMNLP'24 : NLP for Science Workshop (Archival; ACL Anthology: https://aclanthology.org/2024.nlp4science-1.22/)
发表信息：
Proceedings of the 1st Workshop on NLP for Science (NLP4Science), EMNLP 2024
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出将认知工效学融入 LLM 系统设计，构建综合框架与伦理开发指南，以减少偏见、改善体验并提升人机交互的安全性和可靠性。

摘要：

将认知工效学与 LLM 相结合，对于提升人机交互中的安全性、可靠性和用户满意度至关重要。当前的 LLM 设计往往缺乏这种整合，导致系统可能无法充分契合人类的认知能力与局限。这种忽视加剧了 LLM 输出中的偏见，并由于以用户为中心的设计原则应用不一致而造成欠佳的用户体验。研究人员正越来越多地利用 NLP，尤其是 LLM，对社会科学、心理学、精神病学、健康和神经科学领域的人类行为进行建模与理解。我们的立场论文探讨了将认知工效学融入 LLM 设计的必要性，并为合乎伦理的开发提供了全面框架和实践指南。通过应对这些挑战，我们旨在推动更安全、更可靠且伦理稳健的人机交互。

英文摘要：

Integrating cognitive ergonomics with LLMs is crucial for improving safety, reliability, and user satisfaction in human-AI interactions. Current LLM designs often lack this integration, resulting in systems that may not fully align with human cognitive capabilities and limitations. This oversight exacerbates biases in LLM outputs and leads to suboptimal user experiences due to inconsistent application of user-centered design principles. Researchers are increasingly leveraging NLP, particularly LLMs, to model and understand human behavior across social sciences, psychology, psychiatry, health, and neuroscience. Our position paper explores the need to integrate cognitive ergonomics into LLM design, providing a comprehensive framework and practical guidelines for ethical development. By addressing these challenges, we aim to advance safer, more reliable, and ethically sound human-AI interactions.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑