Bryan Wilie

Hi there 👋, thanks for stopping by!

I am a PhD Candidate at The Hong Kong University of Science and Technology in the Department of Electronic and Computer Engineering and I am co-advised by Pascale Fung and Junxian He. Before that, I received the bachelor degree in Electrical Engineering from Bandung Institute of Technology in 2014.

I am generally open for machine learning research internship jobs for fall and spring terms.

Research

I am generally interested in natural language processing and machine learning, specifically in:

Reasoning
Knowledge-intensive NLP
Conversational Al
Low-resource languages

Service

Area Chair at ACL24, NAACL24
Reviewer at AACL, ACL, EMNLP, EACL

Selected Publications

PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems

Bryan Wilie , Yan Xu , Willy Chung , and 3 more authors

In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) , 2023

Abs Paper

Grounding dialogue response generation on external knowledge is proposed to produce informative and engaging responses. However, current knowledge-grounded dialogue (KGD) systems often fail to align the generated responses with human-preferred qualities due to several issues like hallucination and the lack of coherence. Upon analyzing multiple language model generations, we observe the presence of alternative generated responses within a single decoding process. These alternative responses are more faithful and exhibit a comparable or higher level of relevance to prior conversational turns compared to the optimal responses prioritized by the decoding processes. To address these challenges and driven by these observations, we propose Polished & Informed Candidate Scoring (PICK), a generation re-scoring framework that empowers models to generate faithful and relevant responses without requiring additional labeled data or model tuning. Through comprehensive automatic and human evaluations, we demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history. Furthermore, PICK consistently improves the system’s performance with both oracle and retrieved knowledge in all decoding strategies. We provide the detailed implementation in https://github.com/bryanwilie/pick .