research
∙
06/02/2023
KL-Divergence Guided Temperature Sampling
Temperature sampling is a conventional approach to diversify large langu...
share
research
∙
02/11/2023
Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language Models
Despite recent progress, it has been difficult to prevent semantic hallu...
research
∙
10/13/2022
Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence
AI researchers have posited Dungeons and Dragons (D D) as a challenge ...
research
∙
12/23/2021
Measuring Attribution in Natural Language Generation Models
With recent improvements in natural language generation (NLG) models for...
research
∙
12/16/2021
CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
For open-domain conversational question answering (CQA), it is important...
research
∙
07/14/2021
Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features
Knowledge-grounded dialogue systems are intended to convey information t...
research
∙
04/30/2021
Evaluating Groundedness in Dialogue Systems: The BEGIN Benchmark
Knowledge-grounded dialogue agents are systems designed to conduct a con...
research
∙
09/18/2019
Do We Need Neural Models to Explain Human Judgments of Acceptability?
Native speakers can judge whether a sentence is an acceptable instance o...
research
∙
08/14/2019
Fusion of Detected Objects in Text for Visual Question Answering
To advance models of multimodal context, we introduce a simple yet power...
research
∙
05/29/2018
Visually Grounded, Situated Learning in Neural Models
The theory of situated cognition postulates that language is inseparable...
research
∙
11/30/2017
Learning to Adapt by Minimizing Discrepancy
We explore whether useful temporal neural generative models can be learn...
research
∙
03/26/2017