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

共收录 10305
2512.01109 2025-12-02 cs.CL

How do we measure privacy in text? A survey of text anonymization metrics

如何测量文本中的隐私?文本匿名化度量的调查

Yaxuan Ren, Krithika Ramesh, Yaxing Yao, Anjalie Field

机构 * Johns Hopkins University(约翰霍普金斯大学)

AI总结 本文通过系统调查澄清文本隐私度量标准,分析六个隐私概念与法律标准的契合度,为隐私评估提供指导。

Comments 13 pages, 1 figure, 1 table. To be published in Findings of the Association for Computational Linguistics (AACL-IJCNLP 2025). Related resources at: https://github.com/ryxGuo/privacy-metrics-survey

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.19362 2025-12-02 cs.CV cs.AI cs.CL cs.CY cs.LG

LOTUS: A Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User Preferences

LOTUS: 一种用于从质量到社会偏见和用户偏好的详细图像描述的排行榜

Yusuke Hirota, Boyi Li, Ryo Hachiuma, Yueh-Hua Wu, Boris Ivanovic, Yuta Nakashima, Marco Pavone, Yejin Choi, Yu-Chiang Frank Wang, Chao-Han Huck Yang

机构 * NVIDIA Research(NVIDIA研究)

AI总结 LOTUS是一种用于评估详细图像描述质量、偏见和社会偏见的排行榜,通过定制标准满足不同用户偏好,揭示了模型在不同评估标准上的表现差异。

Comments Accepted to ACL 2025. Leaderboard: huggingface.co/spaces/nvidia/lotus-vlm-bias-leaderboard

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.19361 2025-12-02 cs.CL cs.AI cs.SC cs.SD eess.AS

SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models

SpeechIQ: 大型语言模型在语音理解中的跨认知层级语音智能商

Zhen Wan, Chao-Han Huck Yang, Yahan Yu, Jinchuan Tian, Sheng Li, Ke Hu, Zhehuai Chen, Shinji Watanabe, Fei Cheng, Chenhui Chu, Sadao Kurohashi

机构 * Kyoto University(京都大学) NVIDIA Carnegie Mellon University(卡内基梅隆大学) Institute of Science Tokyo(东京科学研究院)

AI总结 SpeechIQ是一种基于语音的智能评估框架,通过三个认知层级评估大型语言模型在语音理解中的能力,提供统一的比较和识别标注错误与幻觉。

Comments ACL 2025 main. Our Speech-IQ leaderboard is hosted at huggingface.co/spaces/nvidia/Speech-IQ-leaderboard. Speech-IQ Calculator: https://github.com/YukinoWan/SpeechIQ

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.05945 2025-12-02 cs.CL cs.AI cs.LG cs.MA eess.AS

NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model

NeKo:跨模态识别后纠错与任务引导的专家混合语言模型

Yen-Ting Lin, Zhehuai Chen, Piotr Zelasko, Zhen Wan, Xuesong Yang, Zih-Ching Chen, Krishna C Puvvada, Szu-Wei Fu, Ke Hu, Jun Wei Chiu, Jagadeesh Balam, Boris Ginsburg, Yu-Chiang Frank Wang, Chao-Han Huck Yang

机构 * NVIDIA

AI总结 NeKo通过任务引导的专家混合模型,实现跨模态识别后的高效纠错,显著降低WER并提升BLEU分数。

Comments ACL 2025 Industry Track. NeKo LMs: https://huggingface.co/nvidia/NeKo-v0-post-correction

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10297 2025-12-01 cs.CL

Local Hybrid Retrieval-Augmented Document QA

本地混合检索增强文档问答

Paolo Astrino

机构 * Università Ca’ Foscari Venezia(威尼斯大学)

AI总结 本研究提出一种本地混合检索增强的文档问答系统,通过结合语义理解和关键词精度,在不传输数据的情况下实现高准确率的问答,平衡隐私与性能。

Comments 10 pages, 5 figures, 3 tables; conference-style (ACL format); fully local RAG system

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.24199 2025-12-01 cs.CL

Linguistically-Controlled Paraphrase Generation

语言控制的改写生成

Mohamed Elgaar, Hadi Amiri

AI总结 LingConv通过细粒度控制40种语言属性生成高质量改写,显著降低属性误差并提升生成质量。

Comments This paper was published in Findings of ACL: EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21250 2025-11-27 cs.CL

ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision

ReSCORE:无标签迭代检索器训练用于多跳问答的 relevancy-一致性监督

Dosung Lee, Wonjun Oh, Boyoung Kim, Minyoung Kim, Joonsuk Park, Paul Hongsuck Seo

机构 * Dept. of CSE, Korea University(韩国大学计算机科学与工程系) NAVER AI Lab(NAVER AI实验室) NAVER Cloud(NAVER云) University of Richmond(里奇蒙大学)

AI总结 ReSCORE通过无标签数据训练密集检索器,提升多跳问答的检索与回答性能。

Comments 9 pages, 3 figures, ACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01341 2025-11-26 cs.CL

TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models

TurnBench-MS: 一个评估大语言模型多轮多步推理能力的基准

Yiran Zhang, Mo Wang, Xiaoyang Li, Kaixuan Ren, Chencheng Zhu, Usman Naseem

AI总结 TurnBench-MS通过互动破码任务评估大语言模型的多轮多步推理能力,揭示当前模型在复杂推理任务中的显著不足。

Comments Accepted to Findings of the Association for Computational Linguistics: EMNLP 2025

Journal ref Findings of the ACL: EMNLP 2025, pp. 19892-19924, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.18685 2025-11-26 cs.CL

From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation

从生成到检测:一个多模态多任务数据集用于基准测试健康误信息

Zhihao Zhang, Yiran Zhang, Xiyue Zhou, Liting Huang, Imran Razzak, Preslav Nakov, Usman Naseem

机构 * Macquarie University(麦考瑞大学) University of Sydney(悉尼大学) UTS(UTS大学) MBZUAI

AI总结 本文提出MM Health数据集,包含人类和AI生成的多模态健康误信息,用于基准测试可靠性检查、原创性检查和细粒度AI检测。

Comments Accepted to Findings of the Association for Computational Linguistics: EMNLP 2025

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 24245-24260, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12964 2025-11-26 cs.CL

MA-COIR: Leveraging Semantic Search Index and Generative Models for Ontology-Driven Biomedical Concept Recognition

MA-COIR: 利用语义搜索索引和生成模型进行面向本体的生物医学概念识别

Shanshan Liu, Noriki Nishida, Rumana Ferdous Munne, Narumi Tokunaga, Yuki Yamagata, Kouji Kozaki, Yuji Matsumoto

机构 * RIKEN AIP University of Tsukuba(茨川大学) RIKEN R-IH RIKEN BRC Osaka Electro-Communication University(大阪电讯大学)

AI总结 MA-COIR通过结合语义搜索索引和生成模型,提升生物医学领域本体驱动的概念识别能力。

Comments preprint

Journal ref https://aclanthology.org/2025.acl-srw.39/

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.11118 2025-11-26 cs.CL cs.AI

UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning

UMB@PerAnsSumm 2025: 通过提示优化和监督微调增强视角感知摘要

Kristin Qi, Youxiang Zhu, Xiaohui Liang

机构 * Department of Computer Science, University of Massachusetts Boston(计算机科学系,马萨诸塞大学波士顿分校)

AI总结 UMB@PerAnsSumm 2025通过提示优化和监督微调提升视角感知摘要质量,结合关键词和引导信息优化摘要生成过程。

Comments CL4HEALTH NAACL: Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

详情

展开后加载摘要…

URL PDF HTML 收藏
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
2511.17153 2025-11-24 cs.CL

LangMark: A Multilingual Dataset for Automatic Post-Editing

LangMark: 一种多语言数据集用于自动后编辑

Diego Velazquez, Mikaela Grace, Konstantinos Karageorgos, Lawrence Carin, Aaron Schliem, Dimitrios Zaikis, Roger Wechsler

机构 * Welocalize(韦洛卡兹) Duke University(杜克大学)

AI总结 LangMark是一个多语言数据集,用于评估和改进自动后编辑系统,通过大规模标注数据展示大型语言模型在后编辑任务中的有效性。

Comments 15 pages, 8 figures, ACL 2025

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025, pages 32653-32667

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12339 2025-11-21 cs.LG cs.AI

A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning

深入研究对抗后缀学习用于劫持大语言模型:增强的对抗触发学习

Zhe Wang, Yanjun Qi

机构 * University of Virginia(弗吉尼亚大学)

AI总结 ATLA通过增强的对抗触发学习方法,高效生成劫持大语言模型的后缀并提取隐藏系统提示,实现高成功率和低查询消耗。

Comments the Association for Computational Linguistics: NAACL 2025

Journal ref https://aclanthology.org/2025.findings-naacl.394/

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.13246 2025-11-21 cs.CL cs.AI

Atomic Calibration of LLMs in Long-Form Generations

大语言模型在长文本生成中的原子校准

Caiqi Zhang, Ruihan Yang, Zhisong Zhang, Xinting Huang, Sen Yang, Dong Yu, Nigel Collier

机构 * University of Cambridge(剑桥大学) Fudan University(复旦大学) Tencent AI Lab(腾讯AI实验室) The Chinese University of Hong Kong(香港中文大学)

AI总结 本研究提出原子校准方法,用于改进大语言模型在长文本生成中的校准能力,揭示置信度方法与生成过程中置信度变化的关联。

Comments ACL 2025 KnowFM Oral / AACL-IJCNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20429 2025-11-19 cs.CL cs.CV

PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy

Shuhao Guan, Moule Lin, Cheng Xu, Xinyi Liu, Jinman Zhao, Jiexin Fan, Qi Xu, Derek Greene

机构 * University College Dublin(都柏林大学) Trinity College Dublin(都柏林三一学院) University of Toronto(多伦多大学) Shanghai University(上海大学)

Comments ACL 2025 main

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12236 2025-11-18 cs.CL cs.AI cs.LG

Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts

Raavi Gupta, Pranav Hari Panicker, Sumit Bhatia, Ganesh Ramakrishnan

机构 * Columbia University(哥伦比亚大学) IIT Bombay(印度理工学院Bombay) Media and Data Science Research (MDSR) Lab, Adobe(Adobe媒体与数据科学研究实验室)

Comments To appear at International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.04990 2025-11-18 cs.CL

DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting

Mingchen Li, Heng Fan, Song Fu, Junhua Ding, Yunhe Feng

机构 * University of North Texas(北卡罗来纳州立大学) Department of Computer Science and Engineering(计算机科学与工程系) Department of Data Science(数据科学系)

Comments 9 pages, 3 figures, 5 tables

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
2503.03044 2025-11-18 cs.CL cs.HC

QE4PE: Word-level Quality Estimation for Human Post-Editing

Gabriele Sarti, Vilém Zouhar, Grzegorz Chrupała, Ana Guerberof-Arenas, Malvina Nissim, Arianna Bisazza

机构 * CLCG, University of Groningen(格罗宁根大学CLCG中心) ETH Zürich(苏黎世联邦理工学院) CSAI, Tilburg University(蒂尔堡大学CSAI中心)

Comments Accepted by TACL (pre-MIT Press publication version); Code: https://github.com/gsarti/qe4pe. Dataset: https://huggingface.co/datasets/gsarti/qe4pe

Journal ref Transactions of the Association for Computational Linguistics (2025) 13: 1410-1435

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.05348 2025-11-18 cs.CL cond-mat.mtrl-sci cs.AI cs.IR

Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Datasets

Satanu Ghosh, Neal R. Brodnik, Carolina Frey, Collin Holgate, Tresa M. Pollock, Samantha Daly, Samuel Carton

机构 * University of New Hampshire(新罕布什尔大学) University of California, Santa Barbara(加州大学圣芭芭拉分校)

Comments LLM for information extraction. Update on 12/11/2024: We added some relevant literature that we missed in the previous version of the paper. Update on 05/25/2025: We changed the metadata

Journal ref Findings of the Association for Computational Linguistics: ACL 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11473 2025-11-17 cs.CL cs.SD eess.AS

Proactive Hearing Assistants that Isolate Egocentric Conversations

Guilin Hu, Malek Itani, Tuochao Chen, Shyamnath Gollakota

机构 * Paul G. Allen School of Computer Science & Engineering, University of Washington(保罗·G·艾伦计算机科学与工程学院,华盛顿大学)

Comments Accepted at EMNLP 2025 Main Conference

Journal ref In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 25377-25394, Suzhou, China. Association for Computational Linguistics

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10780 2025-11-17 cs.CL cs.AI

TEDxTN: A Three-way Speech Translation Corpus for Code-Switched Tunisian Arabic - English

Fethi Bougares, Salima Mdhaffar, Haroun Elleuch, Yannick Estève

Comments The Third Arabic Natural Language Processing Conference. Association for Computational Linguistics. 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10660 2025-11-17 cs.CL cs.AI cs.IT math.IT

Test-Time Steering for Lossless Text Compression via Weighted Product of Experts

Qihang Zhang, Muchen Li, Ziao Wang, Renjie Liao, Lele Wang

机构 * University of British Columbia(不列颠哥伦比亚大学) Vector Institute for AI(人工智能向量研究所) Canada CIFAR AI Chair(加拿大CIFAR人工智能主席) University of Michigan(密歇根大学)

Comments 8 pages. Accepted by EMNLP 2025. Code and additional details are available at: https://qihang-zhang.com/Learning-Sys-Blog/2025/10/15/weighted-product-of-experts.html

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2025, pages 2076-2088, Suzhou, China, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.10202 2025-11-17 cs.CL cs.CV

Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval

Shubhashis Roy Dipta, Francis Ferraro

机构 * Department of Computer Science and Electrical Engineering University of Maryland Baltimore County(计算机科学与电气工程系马里兰大学巴尔的摩县)

Comments Accepted in IJCNLP-AACL 2025 (also presented in MAGMAR 2025 at ACL 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10090 2025-11-14 cs.CL

ELYADATA & LIA at NADI 2025: ASR and ADI Subtasks

Haroun Elleuch, Youssef Saidi, Salima Mdhaffar, Yannick Estève, Fethi Bougares

Comments Published in Proceedings of the ArabicNLP 2025 Workshop (co-located with EMNLP 2025), Association for Computational Linguistics, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏