An Open-Domain QA System for e-Governance

RoLegalGEC：用于罗马尼亚语法律领域语法错误检测与纠正的数据集

RoLegalGEC: Legal Domain Grammatical Error Detection and Correction Dataset for Romanian

本文提出RoLegalGEC数据集，包含35万条法律文本中的语法错误及标注，评估多种神经网络模型用于检测和纠正语法错误，丰富罗马尼亚语研究资源。

基于跨语言领域自适应和侧抑制的罗马尼亚语端到端唇读

End-to-End Lip Reading in Romanian with Cross-Lingual Domain Adaptation and Lateral Inhibition

针对罗马尼亚语唇读数据不足的问题，本文在 Wild LRRo 上比较多种架构与正则化后端，并利用英语、德语未标注视频进行跨语言领域自适应，加入神经侧抑制层，取得当前最优结果。

源自《谁想成为百万富翁？》视频的文化丰富的罗马尼亚语NLP数据集

A Culturally-Rich Romanian NLP Dataset from "Who Wants to Be a Millionaire?" Videos

本文构建了一个源自罗马尼亚版《谁想成为百万富翁？》视频的文化丰富问答数据集，并通过基准、机器翻译和跨语言实验揭示LLM在本土文化问题上的性能短板。

使用长文本编码器改进罗马尼亚语法律判决预测

Improving Legal Judgement Prediction in Romanian with Long Text Encoders

针对法律领域长文档特性导致通用NLP模型难以直接应用的问题，本研究探索了专用模型与通用模型在罗马尼亚语法律判决预测任务上的表现，重点研究Transformer模型的序列长度扩展方法，通过4个不同规模的罗马尼亚语LJP数据集实验，验证了专用模型和长文本处理对性能提升的关键作用。

RoBiologyDataChoiceQA：一个用于提升大型语言模型生物学理解能力的罗马尼亚语数据集

RoBiologyDataChoiceQA: A Romanian Dataset for improving Biology understanding of Large Language Models

本文构建含约14,000题的罗马尼亚语生物选择题数据集RoBiologyDataChoiceQA，并通过基准测试、提示工程与微调实验评估LLM的科学推理及低资源语言领域理解能力。

面向罗马尼亚语医疗问答的大型基准测试

A Large-Scale Benchmark for Evaluating Large Language Models on Medical Question Answering in Romanian

本文提出首个罗马尼亚语医疗问答基准测试MedQARo，评估了多种LLM在医疗问答任务中的表现，发现微调模型在泛化能力上优于零样本模型。

RO-N3WS：利用多样的罗马尼亚语音基准提升低资源ASR的泛化能力

RO-N3WS: Enhancing Generalization in Low-Resource ASR with Diverse Romanian Speech Benchmarks

RO-N3WS通过多样化的罗马尼亚语音数据集提升低资源ASR在零样本和分布外条件下的泛化能力，验证了有限微调对WER的显著提升。

ESGenius：对环境、社会和治理（ESG）及可持续性知识的LLM基准测试

ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge

ESGenius是首个针对LLM在ESG及可持续性知识评估的综合问答基准，通过RAG方法显著提升模型性能。

检索改进并不保证更好的答案：RAG在人工智能政策问答中的研究

Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA

本文研究了RAG在人工智能治理中的应用，发现领域特定微调虽提升检索指标，但未必改善问答性能，尤其在相关文档缺失时可能导致更自信的幻觉。

A Simple Baseline to Semi-Supervised Domain Adaptation for Machine Translation

State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. As data collection is expensive and infeasible in many cases, domain adaptation methods are needed. In this work, we propose a simple but effect approach to the semi-supervised domain adaptation scenario of NMT, where the aim is to improve the performance of a translation model on the target domain consisting of only non-parallel data with the help of supervised source domain data. This approach iteratively trains a Transformer-based NMT model via three training …

Detecting ESG topics using domain-specific language models and data augmentation approaches

Despite recent advances in deep learning-based language modelling, many natural language processing (NLP) tasks in the financial domain remain challenging due to the paucity of appropriately labelled data. Other issues that can limit task performance are differences in word distribution between the general corpora - typically used to pre-train language models - and financial corpora, which often exhibit specialized language and symbology. Here, we investigate two approaches that may help to mitigate these issues. Firstly, we experiment with further language model pre-training using large amoun…