From google gemini to openai q*(q-star): A survey of reshaping the generative artificial intelligence (ai) research landscape
This comprehensive survey explored the evolving landscape of generative Artificial
Intelligence (AI), with a specific focus on the transformative impacts of Mixture of Experts …
Intelligence (AI), with a specific focus on the transformative impacts of Mixture of Experts …
Leveraging large language models in conversational recommender systems
L Friedman, S Ahuja, D Allen, Z Tan… - arXiv preprint arXiv …, 2023 - arxiv.org
A Conversational Recommender System (CRS) offers increased transparency and control to
users by enabling them to engage with the system through a real-time multi-turn dialogue …
users by enabling them to engage with the system through a real-time multi-turn dialogue …
Statistical perspective of top-k sparse softmax gating mixture of experts
Top-K sparse softmax gating mixture of experts has been widely used for scaling up massive
deep-learning architectures without increasing the computational cost. Despite its popularity …
deep-learning architectures without increasing the computational cost. Despite its popularity …
On least squares estimation in softmax gating mixture of experts
Mixture of experts (MoE) model is a statistical machine learning design that aggregates
multiple expert networks using a softmax gating function in order to form a more intricate and …
multiple expert networks using a softmax gating function in order to form a more intricate and …
A general theory for softmax gating multinomial logistic mixture of experts
Mixture-of-experts (MoE) model incorporates the power of multiple submodels via gating
functions to achieve greater performance in numerous regression and classification …
functions to achieve greater performance in numerous regression and classification …
AI Text-to-Behavior: A Study In Steerability
D Noever, S Hyams - arXiv preprint arXiv:2308.07326, 2023 - arxiv.org
The research explores the steerability of Large Language Models (LLMs), particularly
OpenAI's ChatGPT iterations. By employing a behavioral psychology framework called …
OpenAI's ChatGPT iterations. By employing a behavioral psychology framework called …
DGPO: discovering multiple strategies with diversity-guided policy optimization
Most reinforcement learning algorithms seek a single optimal strategy that solves a given
task. However, it can often be valuable to learn a diverse set of solutions, for instance, to …
task. However, it can often be valuable to learn a diverse set of solutions, for instance, to …
Be Helpful but Don't Talk too Much-Enhancing Helpfulness in Conversations through Relevance in Multi-Turn Emotional Support
For a conversation to help and support, speakers should maintain an “effect-effort” tradeoff.
As outlined in the gist of “Cognitive Relevance Principle”, helpful speakers should optimize …
As outlined in the gist of “Cognitive Relevance Principle”, helpful speakers should optimize …
Offline reinforcement learning for mixture-of-expert dialogue management
Reinforcement learning (RL) has shown great promise for developing agents for dialogue
management (DM) that are non-myopic, conduct rich conversations, and maximize overall …
management (DM) that are non-myopic, conduct rich conversations, and maximize overall …
Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
The softmax gating function is arguably the most popular choice in mixture of experts
modeling. Despite its widespread use in practice, softmax gating may lead to unnecessary …
modeling. Despite its widespread use in practice, softmax gating may lead to unnecessary …