Jatin Ganhotra

Learning End-to-End Goal-Oriented Dialog with Multiple Answers

2018 · arXiv (Cornell University)

In a dialog, there can be multiple valid next utterances at any point. The present end-to-end neural methods for dialog do not take this into account. They learn with the assumption that at any time …

Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks

2021 · arXiv (Cornell University)

Explaining neural network models is important for increasing their trustworthiness in real-world applications. Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or detecting interactions between adjacent features. However, …

Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations

2024 · arXiv (Cornell University)

We introduce a structured chain-of-thought (SCoT) prompting approach to generating content-grounded multi-turn question-answer conversations using a pre-trained large language model (LLM). At the core of our proposal is a structured breakdown of the complex task …