The Flan Collection. Designing Data and Methods for Effective Instruction Tuning

ArXiv 2022.

Scaling Instruction-Finetuned Language Models

ArXiv 2022.

You Reap What You Sow: On the Challenges of Bias Evaluation Under Multilingual Settings

ACL 2022 BigScience Workshop.

Active Learning Over Multiple Domains in Natural Language Tasks

NeurIPS Workshop on Distribution Shift 2022.

Entity-Based Knowledge Conflicts in Question Answering

EMNLP 2021.

Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP

ACL 2021.

MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering

TACL 2021.

Invigorating Competition in Social Networking: An Interoperability Remedy that Addresses Data Network Effects and Privacy Concerns

CPI Antitrust Chronicle, June 2021

On the Transferability of Minimal Prediction Preserving Inputs in Question Answering

NAACL 2021.

Open-Domain Question Answering Goes Conversational via Question Rewriting

NAACL 2021.