Showing 2024Show all
3 papers · 1 filter
cs.CL2024
Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability
Ruixi Lin, Yang You
Large language models (LLMs) often struggle with balanced class accuracy in text classification tasks using in-context learning (ICL), hindering some practical uses due to user dis…
cs.CR2024
Can a large language model be a gaslighter?
Wei Li, Luyao Zhu, Yang Song +3
Large language models (LLMs) have gained human trust due to their capabilities and helpfulness. However, this in turn may allow LLMs to affect users' mindsets by manipulating langu…
cs.CL2024
Optimizing Class-Level Probability Reweighting Coefficients for Equitable Prompting Accuracy
Ruixi Lin, Yang You
Even as we engineer LLMs for alignment and safety, they often uncover biases from pre-training data's statistical regularities (from disproportionate co-occurrences to stereotypica…