controlled decoding 1efficiency 1large language models 1preference optimization 1sequence labeling 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
DIRECT: Direct Decoding for Efficient and Aligned Sequence Labeling with Large Language Models
Yilei Wang, Jiaxin Gan, Kexuan Zhang +3
The paper introduces DIRECT, a framework that improves large language model‑based sequence labeling by applying Direct Preference Optimization for better task alignment and a contr…
cs.CL2025
Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations
Peichao Lai, Jiaxin Gan, Feiyang Ye +2
Sequence labeling remains a significant challenge in low-resource, domain-specific scenarios, particularly for character-dense languages like Chinese. Existing methods primarily fo…