Multilingual sequence-to-sequence models perform poorly with increased language coverage and fail to consistently generate text in the correct target language in few-shot settings. To address these challenges, we propose mmT5, a modular multilingual sequence-to-sequence model. mmT5 utilizes language-specific modules during pre-training, which disentangle language-specific information from language-agnostic information. We identify representation drift during fine-tuning as a key limitation of modular generative models and develop strategies that enable effective zero-shot transfer. Our model outperforms mT5 at the same parameter sizes by a large margin on representative natural language understanding and generation tasks in 40+ languages. Compared to mT5, mmT5 raises the rate of generating text in the correct language under zero-shot settings from 7% to 99%, thereby greatly alleviating the source language hallucination problem.
Hallucinations in Large Multilingual Translation Models
Instituto de Telecomunicações(电信研究所);Instituto Superior Técnico, University of Lisbon(里斯本大学高等技术学院);University of Edinburgh(爱丁堡大学);CentraleSupélec, Université Paris-Saclay(巴黎萨克雷大学中央理工-高等电力学院);Unbabel(Unbabel公司)
AraHalluEval: A Fine-grained Hallucination Evaluation Framework for Arabic LLMs
Information and Computer Science Department, King Fahd University of Petroleum and Minerals(信息与计算机科学系,国王法赫德石油和矿物大学);SDAIA-KFUPM Joint Research Center for Artificial Intelligence(SDAIA-KFUPM人工智能联合研究中心)
SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes
University of Helsinki(赫尔辛基大学);SiLO;Université de Lorraine & ICANS Strasbourg(洛林大学及斯特拉斯堡ICANS);Université Bretagne Sud(布列塔尼南方大学);CIMAT A. C.;University of Milano-Bicocca(米兰-布雷拉大学);TU Darmstadt(德累斯顿技术大学);Aveni;Charles University(查尔斯大学);HiTZ Basque Center for Language Technology - Ixa(巴斯克语言技术中心-ixa)
CCNU at SemEval-2025 Task 3: Leveraging Internal and External Knowledge of Large Language Models for Multilingual Hallucination Annotation
Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning(湖北省人工智能与智能学习重点实验室);National Language Resources Monitoring and Research Center for Network Media(网络媒体语言资源监测与研究中心);School of Computer Science, Central China Normal University(中央财经大学计算机学院)
MASSIVE Multilingual Abstract Meaning Representation: A Dataset and Baselines for Hallucination Detection
Paul G. Allen School of Computer Science & Engineering(保罗·G·艾伦计算机科学与工程学院);Georgetown University(乔治城大学);University of Colorado Boulder(科罗拉多大学博尔德分校);Amazon(亚马逊)
Mitigating Multilingual Hallucination in Large Vision-Language Models
School of Computer Science & Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院);School of Computing Science and Technology, Fudan University(复旦大学计算机科学技术学院);Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);School of Computing Science and Technology, Zhejiang Gongshang University(浙江工商大学计算机科学与技术学院);Department of Computer Science and Engineering, The Chinese University of Hong Kong(香港中文大学计算机科学与工程学系)
Output Language Confusion under Multilingual Prompt Contamination
University of Tübingen(蒂宾根大学);Artificial Intelligence Institute, University of South Carolina(南卡罗来纳大学人工智能研究所);Thapar Institute of Engineering & Technology(塔帕尔工程技术学院);Indian Institute of Technology Kanpur(印度理工学院坎普尔分校);Indian AI Research Organization(印度人工智能研究组织)
To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs
Kyutai;Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Institute of Intelligent Systems and Robotics(智能系统与机器人研究所);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Grenoble INP(格勒诺布尔国立理工学院);LIG(格勒诺布尔信息学实验室)
NCL-UoR at SemEval-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified RefChecker and Modified SeflCheckGPT
School of Computing, Newcastle University(新萨勒姆大学计算机学院);Department of Computer Science, University of Reading(阅读大学计算机科学系);Previously at School of Computing, Newcastle University(新萨勒姆大学计算机学院)
Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection
Charles University, Prague(查尔斯大学,布拉格);Independent Researcher(独立研究者);University of Helsinki, Finland(赫尔辛基大学);University of British Columbia, Vancouver, Canada(不列颠哥伦比亚大学,温哥华,加拿大);Chosun University, South Korea(成均馆大学,韩国)
Training Multilingual Machine Translation by Alternately Freezing Language-Specific Encoders-Decoders
TALP Research Center(TALP研究中心);Universitat Politècnica de Catalunya(加泰罗尼亚理工大学);IXA NLP Group(IXA自然语言处理组);University of the Basque Country (UPV/EHU)(巴斯克大学(UPV/EHU))
Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment
Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science Technical University of Darmstadt and National Research Center for Applied Cybersecurity ATHENE, Germany(技术大学达姆施塔特计算机科学系通用知识处理实验室(UKP实验室)和应用网络安全国家研究中心ATHENE德国);Center for AI and Data Science, University of Würzburg(人工智能与数据科学中心,乌尔姆大学)