arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing

2025-11-25 至 2025-11-25 共收录 6
2511.18889 2025-11-25 cs.CL cs.AI

CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation

CoreEval: 通过现实世界知识自动构建抗污染数据集以实现可靠的LLM评估

Jingqian Zhao, Bingbing Wang, Geng Tu, Yice Zhang, Qianlong Wang, Bin Liang, Jing Li, Ruifeng Xu

机构 * Harbin Institute of Technology(哈尔滨工业大学) Peng Cheng Laboratory(鹏城实验室) Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies(广东省新型安全智能技术重点实验室) The Chinese University of Hong Kong(香港中文大学) The Hong Kong Polytechnic University(香港理工大学)

AI总结 CoreEval通过现实世界知识自动更新数据集,提升LLM评估的抗污染能力,减少数据污染导致的性能高估问题。

Comments ACL'25

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.22006 2025-11-25 cs.CL cs.LG

Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them

通过LLM生成数据增强领域特定编码器模型:如何利用本体论,以及如何不依赖本体论

Marc Brinner, Tarek Al Mustafa, Sina Zarrieß

机构 * Computational Linguistics Department of Linguistics(计算语言学系) Institute of Computer Science(计算机科学研究所) Bielefeld University(比勒菲尔德大学)

AI总结 通过LLM生成数据增强领域特定编码器模型,利用本体论或自动提取概念,实现低资源环境下的高效预训练。

Comments Published in the Findings of the Association for Computational Linguistics: EMNLP 2025

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2025 (pp. 22740-22754). Association for Computational Linguistics

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.15289 2025-11-25 cs.CR cs.AI cs.CL

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage

SATA: 一种通过简单辅助任务链接实现LLM劫持的范式

Xiaoning Dong, Wenbo Hu, Wei Xu, Tianxing He

机构 * Tsinghua University(清华大学) Shanghai Qi Zhi Institute(上海启智研究院) Hefei University of Technology(合肥工业大学)

AI总结 SATA通过简单辅助任务链接实现LLM劫持,有效绕过安全措施并提升攻击成功率

Comments ACL Findings 2025. Welcome to employ SATA as a baseline

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04427 2025-11-25 cs.AI cs.CL

Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance

将模式图嵌入多表问答:一种减少大语言模型依赖的人工引导框架

Xixi Wang, Miguel Costa, Jordanka Kovaceva, Shuai Wang, Francisco C. Pereira

机构 * Chalmers University of Technology(查尔姆斯理工大学)

AI总结 本文提出一种基于图的框架,利用人工整理的关系知识减少对大语言模型的依赖,有效解决多表问答中复杂表格模式链接的问题。

Comments Accepted to EMNLP 2025 findings

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.15018 2025-11-25 cs.CL

Using tournaments to calculate AUROC for zero-shot classification with LLMs

利用竞赛计算零样本分类中LLM的AUROC

WonJin Yoon, Ian Bulovic, Timothy A. Miller

机构 * Boston Children’s Hospital(波士顿儿童医院) Harvard Medical School(哈佛医学院)

AI总结 本文提出利用LLM进行零样本分类的AUROC计算,通过成对比较和Elo评分系统提升分类性能并提供更多信息。

Comments The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025, Findings). The code is available at: https://github.com/Machine-Learning-for-Medical-Language/cnlp_llm

Journal ref In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 23583-23591, Suzhou, China. Association for Computational Linguistics

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.15503 2025-11-25 cs.CL

Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval

Llama2Vec: 无监督适应大型语言模型用于密集检索

Zheng Liu, Chaofan Li, Shitao Xiao, Yingxia Shao, Defu Lian

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Beijing Academy of Artificial Intelligence(北京人工智能研究院) University of Science and Technology of China(中国科学技术大学) The Hong Kong Polytechnic University(香港理工大学)

AI总结 Llama2Vec通过无监督适应LLM提升密集检索性能,实现新的最先进结果。

Comments ACL 2024

详情

展开后加载摘要…

URL PDF HTML 收藏