Related papers: Language Model Tokenizers Introduce Unfairness Bet…
In the presented study, we discover that the so-called "transition freedom" metric appears superior for unsupervised tokenization purposes in comparison to statistical metrics such as mutual information and conditional probability,…
Quantification has been proven to be a particularly difficult linguistic phenomenon for (Multimodal) Large Language Models (MLLMs). However, given that quantification interfaces with the logic, pragmatic, and numerical domains, the exact…
The rapid development of Large Language Models (LLMs) demonstrates remarkable multilingual capabilities in natural language processing, attracting global attention in both academia and industry. To mitigate potential discrimination and…
Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system…
The impact of different multilingual data mixtures in pretraining large language models (LLMs) has been a topic of ongoing debate, often raising concerns about potential trade-offs between language coverage and model performance (i.e., the…
Cross-lingual transfer learning is an important property of multilingual large language models (LLMs). But how do LLMs represent relationships between languages? Every language model has an input layer that maps tokens to vectors. This…
Neural networks have become the state-of-the-art approach for machine translation (MT) in many languages. While linguistically-motivated tokenization techniques were shown to have significant effects on the performance of statistical MT, it…
We present a benchmark suite of four datasets for evaluating the fairness of pre-trained language models and the techniques used to fine-tune them for downstream tasks. Our benchmarks cover four jurisdictions (European Council, USA,…
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…
Since traditional tokenizers are isolated from a downstream task and model, they cannot output an appropriate tokenization depending on the task and model, although recent studies imply that the appropriate tokenization improves the…
Multilingual LLMs demonstrate strong performance across diverse languages, yet there has been limited systematic analysis of how language information is structured within their internal representation space and how it emerges across layers.…
The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its success, a critical challenge persists: long tokens, rich…
Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and…
Massively multilingual sentence representations are trained on large corpora of uncurated data, with a very imbalanced proportion of languages included in the training. This may cause the models to grasp cultural values including moral…
Pretrained language models (PLMs) display impressive performances and have captured the attention of the NLP community. Establishing best practices in pretraining has, therefore, become a major focus of NLP research, especially since…
Subjective well-being is a key metric in economic, medical, and policy decision-making. As artificial intelligence provides scalable tools for modelling human outcomes, it is crucial to evaluate whether large language models (LLMs) can…
Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…
The impact of subword tokenization on language model performance is well-documented for perplexity, with finer granularity consistently reducing this intrinsic metric. However, research on how different tokenization schemes affect a model's…
Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural manner. While techniques can…
Tokenization is a critical component of language model pretraining, yet standard tokenization methods often prioritize information-theoretical goals like high compression and low fertility rather than linguistic goals like morphological…