7 papers · 1 filter
Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
Ziqi Miao, Lijun Li, Yuan Xiong +3
Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulne…
UAQFact: Evaluating Factual Knowledge Utilization of LLMs on Unanswerable Questions
Chuanyuan Tan, Wenbiao Shao, Hao Xiong +4
Handling unanswerable questions (UAQ) is crucial for LLMs, as it helps prevent misleading responses in complex situations. While previous studies have built several datasets to ass…
Evolutionary Guided Decoding: Iterative Value Refinement for LLMs
Zhenhua Liu, Lijun Li, Ruizhe Chen +5
While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs without re-training models, its effective…
Learning to Refuse: Towards Mitigating Privacy Risks in LLMs
Zhenhua Liu, Tong Zhu, Chuanyuan Tan +1
Large language models (LLMs) exhibit remarkable capabilities in understanding and generating natural language. However, these models can inadvertently memorize private information,…
Probing Language Models for Pre-training Data Detection
Zhenhua Liu, Tong Zhu, Chuanyuan Tan +3
Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchm…
DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space
Jianxiang Xiang, Zhenhua Liu, Haodong Liu +3
In real-life conversations, the content is diverse, and there exists the one-to-many problem that requires diverse generation. Previous studies attempted to introduce discrete or G…
Controllable and Diverse Data Augmentation with Large Language Model for Low-Resource Open-Domain Dialogue Generation
Zhenhua Liu, Tong Zhu, Jianxiang Xiang +1
Data augmentation (DA) is crucial to mitigate model training instability and over-fitting problems in low-resource open-domain dialogue generation. However, traditional DA methods…