5 papers
Rethinking Reward Models for Multi-Domain Test-Time Scaling
Dong Bok Lee, Seanie Lee, Sangwoo Park +12
The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning…
FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
Seanie Lee, Sangwoo Park, Dong Bok Lee +5
Low-Rank Adaptation (LoRA), which introduces a product of two trainable low-rank matrices into frozen pre-trained weights, is widely used for efficient fine-tuning of language mode…
SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
Seanie Lee, Dong Bok Lee, Dominik Wagner +5
Deploying large language models (LLMs) in real-world applications requires robust safety guard models to detect and block harmful user prompts. While large safety guard models achi…
Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition
Dominik Wagner, Ilja Baumann, Natalie Engert +4
In this work, we present our submission to the Speech Accessibility Project challenge for dysarthric speech recognition. We integrate parameter-efficient fine-tuning with latent au…
HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
Seanie Lee, Haebin Seong, Dong Bok Lee +6
Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world appli…