Joyce Galang

M.Sc.
(external PhD)

Meetings: by calendar invite only
E-Mail: j.galang@tum.de
Room: FMI 01.05.060
Address: TUM - Fakultät für Informatik, Boltzmannstr. 3, 85748 Garching

Research Interests

My research investigates the robustness and reliability of large language models for high-uncertainty decision-making, with venture capital investment as the primary application domain. Current topics include agent systems, retrieval-augmented reasoning, failure modes of LLMs, and uncertainty quantification. I am especially interested in how a model's own uncertainty becomes entangled with the inherent uncertainty of the decision itself.

Supervision

I supervise a limited number of theses and guided research projects on topics related to my research. If you are interested, please send me an email with your current program (e.g., M.Sc. or B.Sc. in Informatics), a short elevator pitch of your research interests, your CV, and your transcript of records.

Publications

Galang, J. A. C., Mady, A., & Groh, G. (2026). Verify, Then Argue: Claim Verification in Investment Agent Debates. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), Industry Track. Association for Computational Linguistics. (forthcoming)

Galang, J. A. C., Mosca, E., Malberg, S., & Groh, G. (2026). LLMs for Venture Capital Investment: Approaches and Open Problems. In Proceedings of the IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI 2026). Springer Nature.

Bae, J. Y., Malberg, S., Galang, J. A. C., Retterath, A., & Groh, G. (2026). DIALECTIC: A Multi-Agent System for Startup Evaluation. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), Industry Track (pp. 711–727). Association for Computational Linguistics.