-
PINE: Position-INvariant inferencE
Position Bias in LLMs
-
Found in the Middle
Permutation Self-Consistency Improves Listwise Ranking in Large Language Models
-
SafeEdit
Detoxifying Large Language Models via Knowledge Editing
-
Refine-LM
Improving Mitigation of Language Model Stereotypes via Reinforcement Learning
-
Fairness-guided Prompting
Fairness-guided Few-shot Prompting for LLMs