Hiding Text in Large Language Models: Introducing Unconditional Token Forcing Confusion Paper • 2406.02481 • Published Jun 4
Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU? Paper • 2301.11688 • Published Jan 27, 2023
Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages Paper • 2404.02588 • Published Apr 3 • 1
NL-ITI: Optimizing Probing and Intervention for Improvement of ITI Method Paper • 2403.18680 • Published Mar 27
Virtual Prompt Injection for Instruction-Tuned Large Language Models Paper • 2307.16888 • Published Jul 31, 2023 • 6
Instruction-following Evaluation through Verbalizer Manipulation Paper • 2307.10558 • Published Jul 20, 2023 • 3