【演講】Evaluating the Ethical Competence of LLMs

活動日期:2025-02-07
~2025-02-07

Seminar: Evaluating the Ethical Competence of LLMs
Speaker: Prof. Seth Lazar, ANU

Moderator: Prof. Linus Huang, HKUST
Date and Time: Feb 7th (Friday), 12 pm – 1:30 pm Hong Kong Time.
Location: Rm. 3401 (Lift 2), Academic Building, HKUST
Zoom ID: 952 5169 8863 (passcode 402295)
Zoom link

Abstract:
Existing approaches to evaluating LLM ethical competence place too much emphasis on the verdicts—of permissibility and impermissibility—that they render. But ethical competence doesn’t consist in one’s judgments conforming to those of a cohort of crowdworkers. It consists in being able to identify morally relevant features, prioritise among them, associate them with reasons and weave them into a justified conclusion. We identify the limitations of existing evals for ethical competence, provide an account of moral reasoning that can ground better alternatives, and discuss the practical—and philosophical—implications if LLMs ultimately do prove to be adept moral reasoners.

Speaker Bio:
Seth Lazar is Professor of Philosophy at the Australian National University, an Australian Research Council (ARC) Future Fellow, a Distinguished Research Fellow of the University of Oxford Institute for Ethics in AI, a fellow of the Carnegie Endowment for International Peace, and a member of the Executive Committee of the ACM Fairness, Accountability and Transparency Conference. For AY 2024/25 he is also a Senior AI Advisor at the Knight First Amendment Institute, Columbia University. He has worked and published widely on the ethics of war, risk, and AI, and now leads the Machine Intelligence and Normative Theory (MINT) Lab, where he leads research projects in normative philosophy of computing and Sociotechnical AI Safety, funded by the Australian Research Council, the Templeton World Charity Foundation, Insurance Australia Group, Schmidt Sciences, the Survival and Flourishing Fund, Google and OpenAI. His book, *Connected by Code: How AI Structures, and Governs, the Ways We Relate*, based on his 2023 Tanner Lecture on AI and Human Values, is forthcoming with Oxford University Press. Seth also edits the Normative Philosophy of Computing newsletter. 

鄂蘭思想工作坊 - 判斷力與公領域的重構

國立中山大學哲學研究所

鄂蘭思想工作坊:判斷力與公領域的重構

活動日期:2025 年03 月24 日
~ 2025 年03 月24 日
發稿日期:2025 年03 月21 日
為何而動

國立陽明交通大學人文藝術與社會學院

為何而動?:即興之哲學與實踐

活動日期:2025 年03 月21 日
~ 2025 年03 月22 日
發稿日期:2025 年03 月21 日
修養與行動工作坊

國立臺灣大學哲學系

中國哲學中的修養與行動學術工作坊

活動日期:2025 年03 月29 日
~ 2025 年03 月30 日
發稿日期:2025 年03 月21 日
Walker20250324

國立政治大學哲學系國立臺灣大學哲學系

Matthew Walker 系列演講資訊

活動日期:2025 年03 月24 日
~ 2025 年03 月28 日
發稿日期:2025 年03 月21 日
Project-3.jpg

輔仁大學天主教學術研究院

【演講】《Antiqua et Nova》: 天主教會呼籲 AI 不等同於人類智慧

活動日期:2025 年03 月28 日
~ 2025 年03 月28 日
發稿日期:2025 年03 月21 日
游淙淇20250319

國立臺灣師範大學國文學系

【演講】歐洲與非歐洲之間——反思胡塞爾的觀點【演講】

活動日期:2025 年03 月19 日
~ 2025 年03 月19 日
發稿日期:2025 年03 月15 日