On Calibration of LLM-based Guard Models for Reliable Content Moderation
Authors: Hongfu Liu, Hengguan Huang, Hao Wang, Xiangming Gu, Ye Wang | Published: 2024-10-14
LLM性能評価
Can LLMs be Scammed? A Baseline Measurement Study
Authors: Udari Madhushani Sehwag, Kelly Patel, Francesca Mosca, Vineeth Ravi, Jessica Staddon | Published: 2024-10-14
Decoding Secret Memorization in Code LLMs Through Token-Level Characterization
Authors: Yuqing Nie, Chong Wang, Kailong Wang, Guoai Xu, Guosheng Xu, Haoyu Wang | Published: 2024-10-11
PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
Authors: Tingchen Fu, Mrinank Sharma, Philip Torr, Shay B. Cohen, David Krueger, Fazl Barez | Published: 2024-10-11
Detecting Training Data of Large Language Models via Expectation Maximization
Authors: Gyuwan Kim, Yang Li, Evangelia Spiliopoulou, Jie Ma, Miguel Ballesteros, William Yang Wang | Published: 2024-10-10
RealVul: Can We Detect Vulnerabilities in Web Applications with LLM?
Authors: Di Cao, Yong Liao, Xiuwei Shang | Published: 2024-10-10
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
Authors: Tong Wu, Shujian Zhang, Kaiqiang Song, Silei Xu, Sanqiang Zhao, Ravi Agrawal, Sathish Reddy Indurthi, Chong Xiang, Prateek Mittal, Wenxuan Zhou | Published: 2024-10-09
Signal Watermark on Large Language Models
Authors: Zhenyu Xu, Victor S. Sheng | Published: 2024-10-09
Superficial Safety Alignment Hypothesis
Authors: Jianwei Li, Jung-Eun Kim | Published: 2024-10-07
DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech
Authors: Dominika Woszczyk, Soteris Demetriou | Published: 2024-10-05