🧑‍🔬 Tsung-Yi Ho

🏛️ Affiliations

🎓Chinese University of Hong KongHong Kong · China2021–2026 · 176 papersEmployment since 2021 · Professor, Computer Science and Engineeringcurrent🎓National Tsing Hua UniversityHsinchu · Taiwan2015–2024 · 173 papersEmployment 2015–2023 · Professor, Computer Science🎓National Cheng Kung UniversityTainan · Taiwan2009–2015 · 118 papers🎓Technical University of MunichMunich · Germany2015–2019 · 18 papers🎓National Yang Ming Chiao Tung UniversityHsinchu · Taiwan2014–2016 · 13 papers🎓National Taiwan UniversityTaipei · Taiwan2001–2007 · 9 papersEducation 2001–2005 · Ph.D., Electrical Engineering🏢IBMArmonk · United States2022–2024 · 2 papers🏥Chang Gung Memorial HospitalTaipei · Taiwan2021–2022 · 2 papers🏥Linkou Chang Gung Memorial HospitalTaoyuan · Taiwan2021–2022 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets (2026 · 4 citations)
   Open-weight chat models are released with safety alignment, but further fine-tuning, even on harmless data, often erodes these guardrails.
2. Hey, That's My Data! Token-Only Dataset Inference in Large Language Models (2026 · 1 citation)
   Owners who suspect an LLM was trained on their proprietary or copyrighted text usually need log-probabilities to test this. Many commercial APIs, however, return only greedy top-1 tokens. The authors address this token-only setting with CatShift, which uses catastrophic forgetting as an auditing signal.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Robust Adversarial Objects against Deep Learning Models ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetTzungyu Tsai et al.2020 · 127 citations
2. Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning DatasetsAnnual Meeting of the Association for Computational Linguistics (ACL)Lei Hsiung, Tianyu Pang, Yung-Chen Tang, et al.2026 · 4 citations
3. Hey, That's My Data! Token-Only Dataset Inference in Large Language ModelsFindings of the Association for Computational LinguisticsChen Xiong, Zihao Wang, Rui Zhu, et al.2026 · 1 citation

🤝 Co-authors here

5 co-authors with a page, the most papers together first.

• Pin-Yu Chen ×2
• Lei Hsiung
• Tianyu Pang
• Yaoqing Yang
• Zihao Wang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Proceedings of the AAAI Conference on Artificial Intelligence

🔗 Cited by

Papers of our library cite their works 4 times (of the 149,439 papers whose bibliographies we read); 2 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/tsung-yi-ho/