Evaluating Parrots and Sociopathic Liars: A keynote at ICTIR 2023

Author:

Sakai Tetsuya1

Affiliation:

1. Waseda University, Japan

Abstract

At ICTIR 2023, which took place on July 23, 2023 in Taipei, I talked about the dark sides of the Large Language Model (LLM) era, and a tentative framework for auditing LLM-based conversational search systems to protect the users from undesirable system responses. This extended abstract provides a short summary of the one-hour keynote and provides pointers to related resources. In addition, it mentions a few recent developments relevant to the talk. Date : 23 July 2023.

Publisher

Association for Computing Machinery (ACM)

Reference15 articles.

1. Dagstuhl Seminar 23031;Bauer Christine,2023

2. On the Dangers of Stochastic Parrots

3. Guglielmo Faggioli, Laura Dietz, Charles L. A. Clarke, Gianluca Demartini, Matthias Hagen, Claudia Hauff, Noriko Kando, Evangelos Kanoulas, Martin Potthast, Benno Stein, and Henning Wachsmuth. Perspectives on large language models for relevance judgment. In Proceedings of the 2023 ACM SIGIR International Conference on Theory of Information Retrieval, ICTIR '23, page 39--50. Association for Computing Machinery, 2023.

4. Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar Benjamin Newman Binhang Yuan Bobby Yan Ce Zhang Christian Cosgrove Christopher D. Manning Christopher Ré Diana Acosta-Navas Drew A. Hudson Eric Zelikman Esin Durmus Faisal Ladhak Frieda Rong Hongyu Ren Huaxiu Yao Jue Wang Keshav Santhanam Laurel Orr Lucia Zheng Mert Yuksekgonul Mirac Suzgun Nathan Kim Neel Guha Niladri Chatterji Omar Khattab Peter Henderson Qian Huang Ryan Chi Sang Michael Xie Shibani Santurkar Surya Ganguli Tatsunori Hashimoto Thomas Icard Tianyi Zhang Vishrav Chaudhary William Wang Xuechen Li Yifan Mai Yuhui Zhang and Yuta Koreeda. Holistic evaluation of language models 2023. URL https://arxiv.org/abs/2211.09110.

5. Yang Liu, Yuanshun Yao, Jean-Francois Ton, Xiaoying Zhang, Ruocheng Guo, Hao Cheng, Yegor Klochkov, Muhammad Faaiz Taufiq, and Hang Li. Trustworthy LLMs: a survey and guideline for evaluating large language models' alignment, 2023. URL https://arxiv.org/abs/2308.05374.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3