Research

I conduct research in natural language processing and artificial intelligence, guided by two core questions: How can AI preserve linguistic and cultural diversity? And how can large language models become more trustworthy—advancing beyond pattern recognition toward genuine reasoning? I’ve explored these challenges through independent projects, internships, and co–first-author collaborations with research labs at Princeton, UCSC, and Stanford.

See recent updates

Peer-Reviewed Publications

Knowing You Don’t Know: When to Continue Search in Multi-round RAG through Self-Practicing

Association for Computing Machinery (ACM) SIGIR 2025 (21.5% acceptance rate). Joint work at UCSC CS research lab.

Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis

Won Best Paper of Association of Computational Linguistics (ACL) Social Influence in Conversations workshop, EMNLP’24

Generative-Adversarial Networks for Low-Resource Language Data Augmentation in Machine Translation

IEEE: International Conference on Natural Language Processing (ICNLP) 2024

Data Augmentation for Low-Resource Language Machine Translation

Columbia Junior Science Journal 2023–2024 (4% acceptance rate). Columbia University’s flagship student research journal.

Joint Research Projects

Research Blog

BergNet: Classifying Harvard Dining Hall Food Using Deep Learning

Published on Medium and Github. Project work at Harvard on Mathematical Elements in AI (2024)

News

[09/2025] Our paper Reinforcing Thinking through Reasoning-Enhanced Reward models is accepted to NeurIPS 2025 Foundations of Reasoning in Language Models (FoRLM).

[09/2025] Our paper Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals is accepted to NeurIPS 2025.

[07/2025] I am honored to receive the National Science Foundation Student Travel Grant for SIGIR 2025.

[07/2025] Our paper Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals is accepted to ACL 2025 Workshop on Fact Extraction and Verification (FEVER), non-archival.

[06/2025] I am thrilled to begin a collaboration with the Language & Cognition Lab at Stanford.

[04/2025] Our paper Knowing You Don’t Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing is accepted by SIGIR 2025.

[11/2024] I am honored to receive Best Paper for Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis at the Social Influence in Conversations Workshop (EMNLP '25).

[10/2024] My paper Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis is accepted by EMNLP Social Influence in Conversations Workshop '24, hosted by ACL.

[06/2024] I am excited to join as a summer intern with Princeton Civil and Environmental Engineering Lab.

[12/2023] My paper Data Augmentation for Low-Resource Language Machine Translation is accepted by Columbia Junior Science Journal.

[11/2023] My paper Generative-Adversarial Networks for Low-Resource Language Data Augmentation in Machine Translation is accepted by ICNLP '24, IEEE Affiliate.

[08/2023] I am thrilled to join the UC Santa Cruz Information Retrieval and Knowledge Management Lab supervised by Professor Yi Zhang.