Yunjie Liao — accepted AI-conference papers

2025

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models

Jun Rao, Yunjie Liao, Xuebo Liu, Zepeng Lin, Lian Lian, Dong Jin +3

EMNLP 2025

Existing alignment methods for preference optimization of large language models (LLMs) aim to enhance model performance by utilizing pairs of positive and negative samples. However, due to the limited capacity of models in scoring or generating responses, the quality of positive and negative samples

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions

Jun Rao, Xuebo Liu, Lian Lian, Shengjun Cheng, Yunjie Liao, Min Zhang

EMNLP 2024main

With instruction tuning, Large Language Models (LLMs) can enhance their ability to adhere to commands. Diverging from most works focusing on data mixing, our study concentrates on enhancing the model’s capabilities from the perspective of data sampling during training. Drawing inspiration from the h…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗