← Search

Larry Birnbaum

2 accepted papers

2022

Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models

EMNLP 2022finding

How to usefully encode compositional task structure has long been a core challenge in AI. Recent work in chain of thought prompting has shown that for very large neural language models (LMs), explicitly demonstrating the inferential steps involved in a target task may improve performance over end-to…

2021

“It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems

EMNLP 2021main

Conversations aimed at determining good recommendations are iterative in nature. People often express their preferences in terms of a critique of the current recommendation (e.g., “It doesn’t look good for a date”), requiring some degree of common sense for a preference to be inferred. In this work,…