Yixuan Tang
I am a first-year MPhil student in Information Systems at The Hong Kong University of Science and Technology, with a research focus on Natural Language Processing (NLP).
About My Research
My research focuses on advancing natural language processing technologies and their applications in information systems. I'm particularly interested in:
- Retrieval-augmented generation (RAG) for knowledge-intensive tasks
- Domain adaptation of large language models
- Financial NLP applications
- LLM Post-training
- Efficient model architectures
Aim to bridge the gap between cutting-edge NLP research and practical applications in business and finance contexts.
Selected Publications
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
Introduces a comprehensive benchmark for evaluating retrieval-augmented generation systems on complex multi-hop queries, providing standardized datasets and metrics.
Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning
Adversarial Mixup Unlearning
Exploring the Relationship between In-Context Learning and Instruction Tuning
FinEntity: Entity-level Sentiment Classification for Financial Texts
Preprints & Projects
InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning
Domain-specific LLM trained on carefully curated financial datasets for investment analysis tasks, demonstrating strong performance on financial NLP benchmarks.