1 citations · 2 across the 2 of their papers we have counts for
4 papers
Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness
David Demeter, Oshin Agarwal, Simon Ben Igeri +4
Academic literature does not give much guidance on how to build the best possible customer-facing summarization system from existing research components. Here we present analyses t…
Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models
Victor S. Bursztyn, David Demeter, Doug Downey +1
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 mo…
Stolen Probability: A Structural Weakness of Neural Language Models
David Demeter, Gregory Kimmel, Doug Downey
Neural Network Language Models (NNLMs) generate probability distributions by applying a softmax function to a distance metric formed by taking the dot product of a prediction vecto…
Just Add Functions: A Neural-Symbolic Language Model
David Demeter, Doug Downey
Neural network language models (NNLMs) have achieved ever-improving accuracy due to more sophisticated architectures and increasing amounts of training data. However, the inductive…