5 papers
Q-realign: Piggybacking Realignment on Quantization for Safe and Efficient LLM Deployment
Qitao Tan, Xiaoying Song, Ningxi Cheng +6
Public large language models (LLMs) are typically safety-aligned during pretraining, yet task-specific fine-tuning required for deployment often erodes this alignment and introduce…
End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost
Qitao Tan, Xiaoying Song, Jin Lu +9
Quantization is an effective technique to reduce the deployment cost of large language models (LLMs), and post-training quantization (PTQ) has been widely studied due to its effici…
Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation
Anirban Saha Anik, Xiaoying Song, Elliott Wang +3
Large language models (LLMs) incorporated with Retrieval-Augmented Generation (RAG) have demonstrated powerful capabilities in generating counterspeech against misinformation. Howe…
A Hybrid Framework for Subject Analysis: Integrating Embedding-Based Regression Models with Large Language Models
Jinyu Liu, Xiaoying Song, Diana Zhang +3
Providing subject access to information resources is an essential function of any library management system. Large language models (LLMs) have been widely used in classification an…
Echoes of Discord: Forecasting Hater Reactions to Counterspeech
Xiaoying Song, Sharon Lisseth Perez, Xinchen Yu +2
Hate speech (HS) erodes the inclusiveness of online users and propagates negativity and division. Counterspeech has been recognized as a way to mitigate the harmful consequences. W…