Addressing Hallucinations in Generative AI for customer service applications

解决客户服务应用生成人工智能中的幻觉

• 批准号: 10092998
• 金额: $ 133.23万
• 依托单位: ALGOMO LIMITED
• 依托单位国家: 英国
• 项目类别: Collaborative R&D
• 财政年份: 2024
• 资助国家: 英国
• 起止时间: 2024 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=10092998
• 关键词: Addressing; Hallucinations; Generative; AI; customer

Advances in Deep Learning have made Large Language Models (LLMs) a potential game-changer for customer service, as well as other commercial applications. These models can generate natural interactions without explicit instructions or manual data, unlike current conversational Artificial Intelligence (cAI) systems.However, this technology carries the risk of incorrect or fabricated answers, known as 'hallucinations', which can undermine customer trust and harm a company's reputation.In this collaborative project, the consortium consisting of Algomo, YuLife, Natwest and the Universities of Edinburgh and Essex will research and develop technologies that will identify, monitor and address hallucinations for customer service applications.This project fits Algomo perfectly, as it improves upon our core product, a cAI platform, and addresses the market need for trustworthy and reliable generative cAI.By developing a technology that effectively addresses hallucinations, we will increase trust and confidence in the outputs of LLMs, ultimately accelerating their commercial adoption not only for customer service but also for a variety of other use-cases.

深度学习的进步使大型语言模型（LLM）成为客户服务以及其他商业应用的潜在游戏规则改变者。这些模型可以在没有明确指令或手动数据的情况下生成自然的交互，不像当前的会话式人工智能（cAI）系统。然而，这项技术存在错误或捏造答案的风险，即所谓的“幻觉”，这可能会破坏客户的信任并损害公司的声誉。在这个合作项目中，由Algomo，YuLife，Natwest和爱丁堡大学和埃塞克斯大学将研究和开发用于客户服务应用的识别、监控和解决幻觉的技术。这个项目非常适合Algomo，因为它改进了我们的核心产品，一个cAI平台，并解决了市场对值得信赖和可靠的生成cAI的需求。通过开发一种有效解决幻觉的技术，我们将增加对LLM输出的信任和信心，最终加速其商业应用，不仅用于客户服务，还用于各种其他用例。