Related papers: Language Preferences and Practices in Multilingual…
Previous work indicates that large language models exhibit a significant "English bias", i.e. they often perform better when tasks are presented in English. Interestingly, we have observed that using certain other languages in reasoning…
Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilingual benchmarks are often taken as evidence that current encoders transfer reliably across…
Multilingual LLMs often have knowledge disparities across languages, with larger gaps in under-resourced languages. Teaching LLMs to abstain in the face of knowledge gaps is thus a promising strategy to mitigate hallucinations in…
Computing and Internet access are substantially growing markets in Southern Africa, which brings with it increasing demands for local content and tools in indigenous African languages. Since most of those languages are low-resourced,…
Lip reading has received increasing attention in recent years. This paper focuses on the synergy of multilingual lip reading. There are about as many as 7000 languages in the world, which implies that it is impractical to train separate lip…
Multilingual large language models are designed, claimed, and expected to cater to speakers of varied languages. We hypothesise that the current practices of fine-tuning and evaluating these models may not perfectly align with this…
Mobile learning through wireless enabled laptops (say, within a university campus) can make use of the learning management system that is already available through internet or intranet. Without restrictions within the four walls of computer…
English is the predominant language on the web, powering nearly half of the world's top ten million websites. Support for multilingual content is nevertheless growing, with many websites increasingly combining English with regional or…
Most current large language models (LLMs) support a wide variety of languages in addition to English, including high-resource languages (e.g. German, Chinese, French), as well as low-resource ones (e.g. Swahili, Telugu). In addition they…
In a conventional Speech emotion recognition (SER) task, a classifier for a given language is trained on a pre-existing dataset for that same language. However, where training data for a language does not exist, data from other languages…
An evolutionary model for emergence of diversity in language is developed. We investigated the effects of two real life observations, namely, people prefer people that they communicate with well, and people interact with people that are…
Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each training question to a single response language or rely on a fixed dominant language for…
Large Language Models (LLMs) have shown the potential to be valuable teaching tools, with the potential of giving every student a personalized tutor. However, one challenge with using LLMs to learn new concepts is that when learning a topic…
Realignment is a promising strategy to improve cross-lingual transfer in multilingual language models. However, empirical results are mixed and often unreliable, particularly for typologically distant or low-resource languages (LRLs)…
Recent studies show that large language models (LLMs) are powerful tools for working with natural language, bringing advances in many areas of computational linguistics. However, these models face challenges when applied to low-resource…
Multilingual Retrieval-Augmented Generation (mRAG) systems enable language models to answer knowledge-intensive queries with citation-supported responses across languages. While such systems have been proposed, an open questions is whether…
Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…
We discuss how desirable it is that Large Language Models (LLMs) be able to adapt or align their language behavior with users who may be diverse in their language use. User diversity may come about among others due to i) age differences;…
Our book "The Reality of Multi-Lingual Machine Translation" discusses the benefits and perils of using more than two languages in machine translation systems. While focused on the particular task of sequence-to-sequence processing and…
Multilinguality is a core capability for modern foundation models, yet training high-quality multilingual models remains challenging due to uneven data availability across languages. A further challenge is the performance interference that…