6 papers
Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination
Vijay Vankadaru, Asha Matthews, Tanya Roosta +1
Hallucination remains one of the central obstacles to deploying medical LLMs. Yet, even when hallucination can be detected, it is still unclear whether the internal representations…
CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning
Md Anwar Hossen, Fatema Siddika, Juan Pablo Munoz +2
Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learni…
FedReFT: Federated Representation Fine-Tuning with All-But-Me Aggregation
Fatema Siddika, Md Anwar Hossen, J. Pablo Muñoz +3
Parameter-efficient fine-tuning (PEFT) adapts large pre-trained models by updating only a small subset of parameters. Recently, Representation Fine-Tuning (ReFT) has emerged as an…
Federated Multimodal Learning with Dual Adapters and Selective Pruning for Communication and Computational Efficiency
Duy Phuong Nguyen, J. Pablo Munoz, Tanya Roosta +1
Federated Learning (FL) enables collaborative learning across distributed clients while preserving data privacy. However, FL faces significant challenges when dealing with heteroge…
The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs
Bryan Guan, Tanya Roosta, Peyman Passban +1
As large language models (LLMs) become integral to diverse applications, ensuring their reliability under varying input conditions is crucial. One key issue affecting this reliabil…
What is Lost in Knowledge Distillation?
Manas Mohanty, Tanya Roosta, Peyman Passban
Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge dist…