B.S. in Computer Science & Mathematics · Minor in StatisticsHi! I'm Haixiang (Hanson) Tang, an undergraduate at the University of Illinois Urbana-Champaign, studying Computer Science & Mathematics with a minor in Statistics.
My research interests include natural language processing, data selection, and AI agents. My recent work studies evidence selection for retrieval-augmented generation, how scientific novelty relates to recognition, and the evaluation of language model agents. I am currently exploring data selection for reinforcement learning post-training.
I am fortunate to work with Prof. Yu Zhang at Texas A&M University. Previously, I worked with Prof. Linfeng Zhang at Shanghai Jiao Tong University on dataset pruning.
In my spare time, I enjoy jazz and classical music, anime, and ACG games.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
University of Illinois Urbana-ChampaignMinor in StatisticsB.S. in Computer Science & MathematicsSep. 2023 - May 2027
Honors & Awards
-
AAAI-26 Student Scholarship & Volunteer Program2025
Experience
-
Texas A&M UniversityAdvisor: Prof. Yu ZhangResearch InternMay 2025 - Present -
Shanghai Jiao Tong UniversityAdvisor: Prof. Linfeng ZhangResearch InternMay 2024 - Feb 2025
Service
Conference
Reviewer- NeurIPS 2026
- WWW 2026
- ACL Rolling Review (ARR)
- ICLR 2027
Journal
Reviewer- TPAMI
- ACM Computing Surveys
News
Selected Publications (view all )
ConSieve: Constraint-Sensitive Evidence Selection for RAG Context Compression
Under review 2026
ConSieve uses counterfactual supervision to select evidence that satisfies answer-critical query constraints during RAG context compression.
ConSieve: Constraint-Sensitive Evidence Selection for RAG Context Compression
Under review 2026
ConSieve uses counterfactual supervision to select evidence that satisfies answer-critical query constraints during RAG context compression.
Different Forms of Paper Novelty Receive Uneven Recognition
Under review 2026
This study examines how human-rated and language-derived forms of novelty relate to citations and public attention in NLP and machine learning.
Different Forms of Paper Novelty Receive Uneven Recognition
Under review 2026
This study examines how human-rated and language-derived forms of novelty relate to citations and public attention in NLP and machine learning.
UNSEEN: Enhancing Dataset Pruning from a Generalization Perspective
Furui Xu, Shaobo Wang, Jiajun Zhang, Chenghao Sun, Haixiang Tang, Linfeng Zhang
AAAI 2026 Poster
We conduct dataset pruning from the perspective of generalization.
UNSEEN: Enhancing Dataset Pruning from a Generalization Perspective
Furui Xu, Shaobo Wang, Jiajun Zhang, Chenghao Sun, Haixiang Tang, Linfeng Zhang
AAAI 2026 Poster
We conduct dataset pruning from the perspective of generalization.