5 papers
The Scaffold Effect: How Prompt Framing Drives Apparent Multimodal Gains in Clinical VLM Evaluation
Doan Nam Long Vu, Simone Balloccu
Trustworthy clinical AI requires that performance gains reflect genuine evidence integration rather than surface-level artifacts. We evaluate 12 open-weight vision-language models…
Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires
Doan Nam Long Vu, Rui Tan, Lena Moench +9
The development of AI for mental health is hindered by a lack of authentic therapy dialogues, due to strict privacy regulations and the fact that clinical sessions were historicall…
Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation
Doan Nam Long Vu, Timour Igamberdiev, Ivan Habernal
Applying differential privacy (DP) by means of the DP-SGD algorithm to protect individual data points during training is becoming increasingly popular in NLP. However, the choice o…
A Course Shared Task on Evaluating LLM Output for Clinical Questions
Yufang Hou, Thy Thy Tran, Doan Nam Long Vu +4
This paper presents a shared task that we organized at the Foundations of Language Technology (FoLT) course in 2023/2024 at the Technical University of Darmstadt, which focuses on…
DP-NMT: Scalable Differentially-Private Machine Translation
Timour Igamberdiev, Doan Nam Long Vu, Felix Künnecke +3
Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite sig…