← Search

Kirby Kuznia

2 accepted papers

2022

Less is More: Summary of Long Instructions is Better for Program Synthesis

EMNLP 2022main

Despite the success of large pre-trained language models (LMs) such as Codex, they show below-par performance on the larger and more complicated programming related questions. We show that LMs benefit from the summarized version of complicated questions. Our findings show that superfluous informatio…

2022

Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

EMNLP 2022main

How well can NLP models generalize to a variety of unseen tasks when provided with task instructions? To address this question, we first introduce Super-NaturalInstructions, a benchmark of 1,616 diverse NLP tasks and their expert-written instructions. Our collection covers 76 distinct task types, in…