DPO after SFT plus constrained template-filling decoding improves LLM sequence-labeling accuracy and cuts inference time by reusing KV cache for non-label tokens.
Named entity recogni- tion for chinese social media with jointly trained embed- dings,
1 Pith paper cite this work, alongside 403 external citations. Polarity classification is still indexing.
1
Pith paper citing it
403
external citations · OpenAlex
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DIRECT: Direct Decoding for Efficient and Aligned Sequence Labeling with Large Language Models
DPO after SFT plus constrained template-filling decoding improves LLM sequence-labeling accuracy and cuts inference time by reusing KV cache for non-label tokens.