Search

Your search keyword '"Yuan, Xingdi"' showing total 71 results
Start Over Author "Yuan, Xingdi"

Refine your results

more »

more »

more »
71 results on '"Yuan, Xingdi"'

53. Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference

Author

Sordoni, Alessandro, Yuan, Xingdi, Côté, Marc-Alexandre, Pereira, Matheus, Trischler, Adam, Xiao, Ziang, Hosseini, Arian, Niedtner, Friederike, and Roux, Nicolas Le

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Computation and Language, Computation and Language (cs.CL), Machine Learning (cs.LG)
Abstract

We view large language models (LLMs) as stochastic \emph{language layers} in a network, where the learnable parameters are the natural language \emph{prompts} at each layer. We stack two such layers, feeding the output of one layer to the next. We call the stacked architecture a \emph{Deep Language Network} (DLN). We first show how to effectively perform prompt optimization for a 1-Layer language network (DLN-1). We then show how to train 2-layer DLNs (DLN-2), where two prompts must be learnt. We consider the output of the first layer as a latent variable to marginalize, and devise a variational inference algorithm for joint prompt training. A DLN-2 reaches higher performance than a single layer, sometimes comparable to few-shot GPT-4 even when each LLM in the network is smaller and less powerful. The DLN code is open source: https://github.com/microsoft/deep-language-networks .

Published
2023
Full Text
View/download PDF

62. TextWorld: A Learning Environment for Text-based Games

Author

C��t��, Marc-Alexandre, K��d��r, ��kos, Yuan, Xingdi, Kybartas, Ben, Barnes, Tavian, Fine, Emery, Moore, James, Tao, Ruo Yu, Hausknecht, Matthew, Asri, Layla El, Adada, Mahmoud, Tay, Wendy, and Trischler, Adam

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Computation and Language, Statistics - Machine Learning, ComputingMilieux_PERSONALCOMPUTING, Machine Learning (stat.ML), Computation and Language (cs.CL), Machine Learning (cs.LG)
Abstract

We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose features and challenges we have analyzed. More significantly, it enables users to handcraft or automatically generate new games. Its generative mechanisms give precise control over the difficulty, scope, and language of constructed games, and can be used to relax challenges inherent to commercial text games like partial observability and sparse rewards. By generating sets of varied but similar games, TextWorld can also be used to study generalization and transfer learning. We cast text-based games in the Reinforcement Learning formalism, use our framework to develop a set of benchmark games, and evaluate several baseline agents on this set and the curated list., Presented at the Computer Games Workshop at IJCAI 2018, Stockholm

Published
2018

67. NewsQA: A Machine Comprehension Dataset

Author

Trischler, Adam, primary, Wang, Tong, additional, Yuan, Xingdi, additional, Harris, Justin, additional, Sordoni, Alessandro, additional, Bachman, Philip, additional, and Suleman, Kaheer, additional

Published
2017
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results