4 papers · 1 filter
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
San Kim, Gary Geunbae Lee
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without addit…
Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection
San Kim, Jonghwi Kim, Yejin Jeon +1
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by providing external knowledge for accurate and up-to-date responses. However, this reliance on external…
Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning
Wonjun Lee, San Kim, Gary Geunbae Lee
Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue ta…
Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents
San Kim, Gary Geunbae Lee
Recent advancements in open-domain dialogue systems have been propelled by the emergence of high-quality large language models (LLMs) and various effective training methodologies.…