5 papers
Understanding the Role of Prompt Template in Knowledge Distillation for Safety Alignment
Anjila Budathoki, Manish Dhakal, Benjamin M. Ampel +1
Prior research has demonstrated that the choice of prompt template during Supervised Fine-Tuning (SFT) significantly impacts the robustness of safety alignment afterwards. However,…
Authority Bias in Conversational Search Engines for Academic Paper Recommendation
Uthman Jinadu, Parsa Ghazvinian, Anjila Budathoki +3
Large Language Models (LLMs) are increasingly used as conversational search engines for academic literature, yet whether they judge papers on content or on authority signals has no…
Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks
Dipesh KC, Anjila Budathoki
Coding-agent benchmarks evaluate whether a single uninterrupted agent can resolve a repository issue. Real software work is messier: tasks are interrupted, reassigned, reviewed, an…
DistillLens: Symmetric Knowledge Distillation Through Logit Lens
Manish Dhakal, Uthman Jinadu, Anjila Budathoki +2
Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process…
Adversarial Robustness Analysis of Vision-Language Models in Medical Image Segmentation
Anjila Budathoki, Manish Dhakal
Adversarial attacks have been fairly explored for computer vision and vision-language models. However, the avenue of adversarial attack for the vision language segmentation models…