11 citations · 12 across the 3 of their papers we have counts for
5 papers · 1 filter
KL-Divergence Guided Temperature Sampling
Chung-Ching Chang, David Reitter, Renat Aksitov +1
Temperature sampling is a conventional approach to diversify large language model predictions. As temperature increases, the prediction becomes diverse but also vulnerable to hallu…
How do decoding algorithms distribute information in dialogue responses?
Saranya Venkatraman, He He, David Reitter
Humans tend to follow the Uniform Information Density (UID) principle by distributing information evenly in utterances. We study if decoding algorithms implicitly follow this UID p…
Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features
Hannah Rashkin, David Reitter, Gaurav Singh Tomar +1
Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative…
Do We Need Neural Models to Explain Human Judgments of Acceptability?
Wang Jing, M. A. Kelly, David Reitter
Native speakers can judge whether a sentence is an acceptable instance of their language. Acceptability provides a means of evaluating whether computational language models are pro…
Fusion of Detected Objects in Text for Visual Question Answering
Chris Alberti, Jeffrey Ling, Michael Collins +1
To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language. The "Bounding Boxes in Text Tran…