Performance prediction is a method to estimate the performance of Language Models (LMs) on various Natural Language Processing (NLP) tasks, mitigating computational costs associated with model capacity and data for fine-tuning. Our paper presents ProxyLM, a scalable task- and language-agnostic framework designed to predict the performance of LMs using proxy models. These proxy models act as surrogates, approximating the performance of the LM of interest. By leveraging these proxy models, ProxyLM significantly reduces computational overhead in task evaluations, achieving up to a 37.08x speedup over traditional methods, even with our smallest proxy models. Our results across multiple multilingual NLP tasks and various robustness tests demonstrate that ProxyLM not only adapts well to previously unseen languages in pre-trained LMs, but also generalizes effectively across different datasets, outperforming the state-of-the-art by at least 1.78x in terms of root-mean-square error (RMSE).
Translation as a Scalable Proxy for Multilingual Evaluation
University of California, Los Angeles(加州大学洛杉矶分校);African Languages Lab(非洲语言实验室);Mila - Quebec AI Institute(魁北克人工智能研究所);McGill University(麦吉尔大学);Canada CIFAR AI Chair(加拿大CIFAR人工智能主席)
The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights
National Key Laboratory for Novel Software Technology(计算机软件新技术国家重点实验室);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Informatics, University of Edinburgh(爱丁堡大学信息学院)
Multilingual Multimodal Learning with Machine Translated Text
Wuhan University of Science and Technology(武汉科技大学);University Politehnica of Bucharest(布加勒斯特理工大学);University of Copenhagen(哥本哈根大学);Pioneer Centre for AI(人工智能先锋中心)
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)
Multilingual Verifier Bias in RLVR: Benchmark, Rollout Diagnosis, and the Cross-Lingual Selection Bottleneck
School of Engineering, Institute of Science Tokyo(科学东京大学工程学院);College of Control Science and Engineering, Zhejiang University(浙江大学控制科学与工程学院);Department of Electrical and Computer Engineering, National University of Singapore(新加坡国立大学电气与计算机工程学院)
Lost in translation: using global fact-checks to measure multilingual misinformation prevalence, spread, and evolution
Department of Mathematical Modeling and Machine Learning, University of Zurich, Switzerland(苏黎世大学数学建模与机器学习系);Digital Society Initiative, University of Zurich, Switzerland(苏黎世大学数字社会倡议);Oxford Internet Institute, University of Oxford, United Kingdom(牛津大学网络研究所);Meedan, San Francisco, United States(梅丹公司,旧金山,美国)