← Search

Chengyu Jiao

2 accepted papers

2026

Embracing Positional Bias in Multiple-Choice Question Answering via Permutation Equivariant Neural Networks

AAAI 2026technical

Several studies have demonstrated that large language models (LLMs) exhibit positional bias when answering multiple-choice questions (MCQs). Previous methods have identified such bias to be detrimental, leading to the development of techniques to mitigate it. However, we observe that certain permuta

Cited by 0SourcePDFScholar
2025

SPE Attention: Making Attention Equivariant to Semantic-Preserving Permutation for Code Processing

EMNLP 2025

Codes serve as the fundamental language for human to communicate with machines, and various Transformer-based models are trained to process codes in recent advancements. A unique symmetry of code is its semantic-preserving permutation, which allows certain lines to be rearranged without altering the

Cited by 0SourcePDFScholar