3 papers
cs.CL2026
Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality
Qipeng Xie, Zi Liang, Jiafei Wu +6
Large Language Models (LLMs) exhibit extreme sensitivity to surface-level prompt variations, in which minor lexical changes can trigger disproportionate performance fluctuations. M…
cs.CL2024
Dissecting Fine-Tuning Unlearning in Large Language Models
Yihuai Hong, Yuelin Zou, Lijie Hu +3
Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabiliti…
cs.CL2024
Intrinsic Test of Unlearning Using Parametric Knowledge Traces
Yihuai Hong, Lei Yu, Haiqin Yang +2
The task of "unlearning" certain concepts in large language models (LLMs) has attracted immense attention recently, due to its importance in mitigating undesirable model behaviours…