Scholarlink

In this paper we introduce a typology of operational issues and negative outcomes associated with public-facing chatbots that generate novel content using large language models (LLMs). Grounded in actual incidents and reports of negative outcomes resulting from chatbots and other LLM applications, the typology represents a key step towards realizing the promise of trustworthy chatbots that maximize benefits and minimize risks to the public. In addition to empowering developers and deployers to work through risks, this typology can also inform a roadmap for researchers to identify gaps and weaknesses in existing assurance tools, indicating priorities for future research. ©2024 The MITRE Corporation. All rights reserved. Approved for public release. Distribution unlimited 24–2767.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

What Happens When Chatbots Go Wild?

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jeff Stanley,
  • Hannah Lettie

摘要

In this paper we introduce a typology of operational issues and negative outcomes associated with public-facing chatbots that generate novel content using large language models (LLMs). Grounded in actual incidents and reports of negative outcomes resulting from chatbots and other LLM applications, the typology represents a key step towards realizing the promise of trustworthy chatbots that maximize benefits and minimize risks to the public. In addition to empowering developers and deployers to work through risks, this typology can also inform a roadmap for researchers to identify gaps and weaknesses in existing assurance tools, indicating priorities for future research. ©2024 The MITRE Corporation. All rights reserved. Approved for public release. Distribution unlimited 24–2767.