Search Results for author: Tianci Xue

Found 3 papers, 0 papers with code

TADIS: Steering Models for Deep-Thinking about Demonstration Examples

no code implementations2 Oct 2023 Tianci Xue, Ziqi Wang, Yixia Li, Yun Chen, Guanhua Chen

To alleviate the illusion of competence of models, we first ask the model to verify the correctness of shown examples.

Instruction Following Zero-shot Generalization

Parameter-Efficient Tuning Helps Language Model Alignment

no code implementations1 Oct 2023 Tianci Xue, Ziqi Wang, Heng Ji

To this end, prior works incorporate controllable generations for alignment to make language models learn multiple preferences and provide outputs with different preferences during inference if asked.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.