Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM

no code implementations • 4 Jan 2024 • Xiaoding Lu, Zongyi Liu, Adian Liusie, Vyas Raina, Vineet Mudupalli, Yuwen Zhang, William Beauchamp

In conversational AI research, there's a noticeable trend towards developing models with a larger number of parameters, exemplified by models like ChatGPT.

The Chai Platform's AI Safety Framework

no code implementations • 5 Jun 2023 • Xiaoding Lu, Aleksey Korshuk, Zongyi Liu, William Beauchamp

Chai empowers users to create and interact with customized chatbots, offering unique and engaging experiences.

Chatbot

Safer Conversational AI as a Source of User Delight

no code implementations • 18 Apr 2023 • Xiaoding Lu, Aleksey Korshuk, Zongyi Liu, William Beauchamp, Chai Research

This work explores the impact of moderation on users' enjoyment of conversational AI systems.

Rewarding Chatbots for Real-World Engagement with Millions of Users

no code implementations • 10 Mar 2023 • Robert Irvine, Douglas Boubert, Vyas Raina, Adian Liusie, Ziyi Zhu, Vineet Mudupalli, Aliaksei Korshuk, Zongyi Liu, Fritz Cremer, Valentin Assassi, Christie-Carol Beauchamp, Xiaoding Lu, Thomas Rialan, William Beauchamp

The proposed approach uses automatic pseudo-labels collected from user interactions to train a reward model that can be used to reject low-scoring sample responses generated by the chatbot model at inference time.

Chatbot Language Modelling