Zhiqi Huang

photo @ Yellowstone

Hi, I am an Applied Researcher at Capital One. I completed my Ph.D. under the mentorship of my advisor, Prof. James Allan, at the Center for Intelligent Information Retrieval (CIIR), Manning College of Information and Computer Sciences, University of Massachusetts Amherst. My research endeavors lie at the intersection of information retrieval, natural language processing, and machine learning (IR/NLP/ML).

I received my master’s in Statistics from the University of Maryland, College Park, and my bachelor’s in Applied Math from Sun Yat-sen University.

news

Feb 20, 2025	Check our survey, A Survey of Model Architectures in Information Retrieval, for the development of information retrieval (IR) modeling and challenges in the era of large language models (LLMs).
Sep 20, 2024	Our paper, Language Concept Erasure for Language-Invariant Dense Retrieval, has been accepted for an oral presentation at the EMNLP 2024 main conference. See you in Miami!
Jul 22, 2024	I’m joining Capital One as an applied researcher.
Jun 26, 2024	I defended my dissertation and completed my Ph.D.
Jun 03, 2024	My internship work with Google, Optimizing Large-Scale Context Retrieval for End-to-end ASR, has been accepted at Interspeech 2024.

selected publications

SIGIR

Soft Prompt Decoding for Multilingual Dense Retrieval

Zhiqi Huang, Hansi Zeng, Hamed Zamani, and James Allan

In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023

PDF
INTERSPEECH

Optimizing Large-Scale Context Retrieval for End-to-End ASR

Zhiqi Huang, Diamantino Caseiro, Kandarp Joshi, Christopher Li, Pat Rondon, Zelin Wu, Petr Zadrazil, and Lillian Zhou

In Interspeech 2024, 2024

PDF
EMNLP

Language Concept Erasure for Language-invariant Dense Retrieval

Zhiqi Huang, Puxuan Yu, Shauli Ravfogel, and James Allan

In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Nov 2024

Abs PDF

Multilingual models aim for language-invariant representations but still prominently encode language identity. This, along with the scarcity of high-quality parallel retrieval data, limits their performance in retrieval. We introduce LANCER, a multi-task learning framework that improves language-invariant dense retrieval by reducing language-specific signals in the embedding space. Leveraging the notion of linear concept erasure, we design a loss function that penalizes cross-correlation between representations and their language labels. LANCER leverages only English retrieval data and general multilingual corpora, training models to focus on language-invariant retrieval by semantic similarity without necessitating a vast parallel corpus. Experimental results on various datasets show our method consistently improves over baselines, with extensive analyses demonstrating greater language agnosticism.