← Search

Zhongkun Liu

2 accepted papers

2024

Self-Supervised Position Debiasing for Large Language Models

ACL 2024findings

Fine-tuning has been demonstrated to be an effective method to improve the domain performance of large language models (LLMs). However, LLMs might fit the dataset bias and shortcuts for prediction, leading to poor generation performance. Previous works have proven that LLMs are prone to exhibit posi…

2021

Learning to Ask Conversational Questions by Optimizing Levenshtein Distance

ACL 2021long

Conversational Question Simplification (CQS) aims to simplify self-contained questions into conversational ones by incorporating some conversational characteristics, e.g., anaphora and ellipsis. Existing maximum likelihood estimation based methods often get trapped in easily learned tokens as all to…