Blog

TLDR We trained a series of 7B LLMs named XGen-7B with standard dense attention on up to 8K sequence length for up to 1.5T tokens. We also fine tune the models on public-domain instructional data. The main take-aways are: * On standard NLP benchmarks, XGen achieves comparable or better results

AUTHORS: Sharvin Shah, Jin Qu, Donald Rose TL;DR: TaiChi is an open source library for few-shot NLP, designed for data scientists and software engineers who want to get some quick results or build proof-of-concept products but don’t have much experience with few-shot learning (FSL). The library abstracts complex

Lead Author: Xi Ye TL;DR: We propose RnG-KBQA, a Rank-and-Generate Approach for Question Answering over Knowledge Bases, which enables answering natural language questions over large-scale knowledge bases. Our approach is capable of answering questions about topics never seen in the training data, which makes it generalizable to a broad

Conference Overview This year marks the 60th annual meeting of the Association for Computational Linguistics Conference (ACL [https://www.2022.aclweb.org/]). ACL is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or

AUTHORS: Tian Xie, Xinyi Yang, Angela Lin, Donald Rose Introduction and Background Creating a system capable of conducting a meaningful conversation with a human and helping them accomplish tasks is one of the ultimate goals of Artificial Intelligence (AI), and has been since AI’s beginnings. Meanwhile, as real conversational

TL;DR: Today’s NLP models, for all their recent successes, have certain limitations. Case in point: they exhibit poor performance when processing multilingual code-mixed sentences (each containing multiple languages). Our new approach addresses this problem by constructing code-mixed inputs designed to degrade (or “attack”) the model, exposing the limitations

Discover CTRLsum, a novel framework for controllable text summarization that enables users to control multiple aspects of generated summaries by interacting with the summarization system through textual input in the form of a set of keywords or descriptive prompts.

August 5, 2021 In June 2021, four of us from the Salesforce AI Ethics and Conversational Design teams collaborated with the Montreal AI Ethics Institute [https://montrealethics.ai/] (MAIEI) to facilitate a workshop on the responsible creation and implementation of chatbots and conversational assistants. Connor Wright [https://www.linkedin.com/

AI can learn the language of biology to create artificial proteins across multiple protein types that are functional and unseen in nature.

An AI model can generate sequences across natural language and proteins with attributes that go beyond the training distribution

This is my obsessively curated list of research papers and articles on ethics in AI that I have been collecting over the years. Ones in bold are those that I refer back to and found particularly useful. Let me know if I am missing your favorites.