English(EN) DIRECT: Direct Decoding for Efficient and Aligned Sequence Labeling with Large Language Models

新的DIRECT框架提高了LLM在序列标注任务中的效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-30 04:00

研究人员推出了一种新颖的DIRECT框架，旨在提高大型语言模型（LLM）在序列标注任务中的效率和领域对齐性。该框架在监督微调后结合了直接偏好优化（DPO），以更好地与人类偏好对齐，并采用受控解码过程，强制执行特定的输出格式并将预测限制在预定义的候选集中。此外，DIRECT利用模板填充机制，仅让模型生成标签令牌来优化推理速度，从而通过KV缓存重用减少计算开销。在八个数据集上的实验表明，DIRECT在性能和效率方面均显著优于现有方法。 AI

影响该框架可能通过LLM实现更高效、更准确的文本信息提取。

排序理由该集群包含一篇详细介绍LLM新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 70 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Yilei Wang, Jiaxin Gan, Kexuan Zhang, Ling Li, Wentao Zhang, Peichao Lai · 2026-07-30 04:00

DIRECT：用于大型语言模型高效且对齐的序列标注的直接解码

arXiv:2607.26891v1 Announce Type: new Abstract: Sequence labeling is a fine-grained information extraction task, yet existing large language model-based approaches suffer from insufficient domain alignment and low inference efficiency. To address these issues, we propose DIRECT, …

本文如何被排名

报道来源 [1]

DIRECT：用于大型语言模型高效且对齐的序列标注的直接解码

相关实体

相关话题