YifeiWang

Intermediate
@wangyifei0047

Pos2Distill-. [EMNLP25] Official code for "POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillation"

38

FASA-ICLR2026. [ICLR 2026] FASA: FREQUENCY-AWARE SPARSE ATTENTION

19

TFRKN. This is the Two-hop Factual Reasoning for Knowledge Neurons (TFRKN) dataset from the paper Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons(EMNLP2024).

2

Z_deepseek_dstill. Jupyter Notebook

1
4
Apply