bilingualism
Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs
Zhang, Xiang, Li, Senyu, Hauer, Bradley, Shi, Ning, Kondrak, Grzegorz
Large Language Models (LLMs) have demonstrated exceptional natural language understanding abilities and have excelled in a variety of natural language processing (NLP)tasks in recent years. Despite the fact that most LLMs are trained predominantly in English, multiple studies have demonstrated their comparative performance in many other languages. However, fundamental questions persist regarding how LLMs acquire their multi-lingual abilities and how performance varies across different languages. These inquiries are crucial for the study of LLMs since users and researchers often come from diverse language backgrounds, potentially influencing their utilization and interpretation of LLMs' results. In this work, we propose a systematic way of qualifying the performance disparities of LLMs under multilingual settings. We investigate the phenomenon of across-language generalizations in LLMs, wherein insufficient multi-lingual training data leads to advanced multi-lingual capabilities. To accomplish this, we employ a novel back-translation-based prompting method. The results show that GPT exhibits highly translating-like behaviour in multilingual settings.
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability
Briakou, Eleftheria, Cherry, Colin, Foster, George
Large, multilingual language models exhibit surprisingly good zero- or few-shot machine translation capabilities, despite having never seen the intentionally-included translation examples provided to typical neural translation systems. We investigate the role of incidental bilingualism -- the unintentional consumption of bilingual signals, including translation examples -- in explaining the translation capabilities of large language models, taking the Pathways Language Model (PaLM) as a case study. We introduce a mixed-method approach to measure and understand incidental bilingualism at scale. We show that PaLM is exposed to over 30 million translation pairs across at least 44 languages. Furthermore, the amount of incidental bilingual content is highly correlated with the amount of monolingual in-language content for non-English languages. We relate incidental bilingual content to zero-shot prompts and show that it can be used to mine new prompts to improve PaLM's out-of-English zero-shot translation quality. Finally, in a series of small-scale ablations, we show that its presence has a substantial impact on translation capabilities, although this impact diminishes with model scale.
People who speak 2 dialects share a cognitive advantage with bilingual people
There has been a lot of research to back up the idea that people who use two or more languages everyday experience significant advantages. The brain training involved in having to use a different language depending on the context and speaker is credited with enhancing attention and memory skills -- as well as better recovery after stroke and even later onset of the symptoms of dementia. But there is another -- often hidden -- source of brain-training in language use which many of us are not even aware of: dialects. Bidialectalism -- which simply means the systematic use of two different dialects of the same language -- is widespread in many parts of the world. In the U.S., millions of children grow up speaking African American Vernacular English at home as well as mainstream American English at school. People who speak two dialects may share a cognitive profile with people who speak two languages.
Being bilingual can be bad for your brain: Scientists say it can damage a person's ability to judge their own performance
More than half of the world's population is bilingual and that prevalence is rising. Psychologists have been interested in how bilingualism shapes the mind for almost a century - and many say it can improve memory and attention. But new research suggests this may not be the case, and being bilingual could in fact be bad for your brain. In their studies, babies listened to words spoken in both Spanish and English, which is common in America. They are those who suggest that in order to speak in one language, bilinguals have to suppress the influence of the other.