← Search

Kuo Liao

2 accepted papers

2024

Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding

ACL 2024long

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters numerous challenges, including the objective mismatch issue, leadi…

2024

Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors

ACL 2024long

Multiple-Choice Questions (MCQs) constitute a critical area of research in the study of Large Language Models (LLMs). Previous works have investigated the selection bias problem in MCQs within few-shot scenarios, in which the LLM’s performance may be influenced by the presentation of answer choices,…