Weiyan Shi

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes

2024

Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current influence estimation techniques involve computing …

Distilling an End-to-End Voice Assistant Without Instruction Training Data

2024 · arXiv (Cornell University)

Voice assistants, such as Siri and Google Assistant, typically model audio and text separately, resulting in lost speech information and increased complexity. Recent efforts to address this with end-to-end Speech Large Language Models (LLMs) trained …

Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval

2024

Kazuaki Furumai, Roberto Legaspi, Julio Cesar Vizcarra Romero, Yudai Yamazaki, Yasutaka Nishimura, Sina Semnani, Kazushi Ikeda, Weiyan Shi, Monica Lam. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

INSPIRED: Toward Sociable Recommendation Dialog Systems

2020

In recommendation dialogs, humans commonly disclose their preference and make recommendations in a friendly manner. However, this is a challenge in developing a sociable recommendation dialog system, due to the lack of dialog dataset annotated …