arXiv cs.CL· Claire Wang·· 11 小时前AI 评分20
用 LLM 处理尼泊尔语推文中 NER 的困难案例
Using an LLM to Tackle Difficult Cases in NER for Nepali Tweets
AI 导读
研究用微调预训练语言模型（PLM）的 token 概率将尼泊尔语推文测试集分为“简单”和“困难”案例，再用 16 种提示词配置评估 LLM 在困难案例上的表现。基于语义相似度选择示例并增加示例数量，可使 F1 分数较基线配置提升近 10 分。LLM 在完整和简单测试集上不及 PLM，但在困难测试集上超过 PLM，两模型结合后得分进一步提升。
正文 · 原文
Abstract:Named entity recognition (NER) is challenging for social media data in a low-resource language. LLMs often lag behind pretrained language models (PLMs) in NER performance, but they show promise in handling cases that PLMs struggle with. Using a dataset of Nepali tweets, we split the test set into "easy" and "hard" cases using token probabilities from a fine-tuned pretrained language model (PLM). We then evaluate an LLM on the hard test cases using 16 different prompt configurations. We find that selecting examples based on semantic similarity and increasing the number of examples improves F1 score by almost 10 points from the baseline configuration. Although the LLM underperforms the PLM on the full and easy test sets, it surpasses the PLM on the hard test set, resulting in an improved score when the two models are combined.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.08967 [cs.CL] |
| (or arXiv:2611.08967v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08967 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Claire Wang [view email]
[v1]
Fri, 6 Nov 2026 04:24:46 UTC (221 KB)
来源：arXiv cs.CL · arxiv.org