相关论文: Contextual morphologically-guided tokenization for…

Tokenization inefficiency imposes structural disadvantages on morphologically complex, low-resource languages, inflating compute resources and depressing accuracy. We evaluate 10 large language models (LLMs) on AfriMMLU (9,000 MCQA items; 5…

Going beyond mere fine-tuning of vision-language models (VLMs), learnable prompt tuning has emerged as a promising, resource-efficient alternative. Despite their potential, effectively learning prompts faces the following challenges: (i)…

We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource…

General-purpose language models are trained to produce varied natural language outputs, but for some tasks, like annotation or classification, we need more specific output formats. LLM systems increasingly support structured output, which…

Fine-tuning large language models (LLMs) with limited data poses a practical challenge in low-resource languages, specialized domains, and constrained deployment settings. While pre-trained LLMs provide strong foundations, effective…

Tokenization plays a pivotal role in multilingual NLP. However, existing tokenizers are often skewed towards high-resource languages, limiting their effectiveness for linguistically diverse and morphologically rich languages such as those…

Training monolingual language models for low and mid-resource languages is made challenging by limited and often inadequate pretraining data. In this study, we propose a novel model conversion strategy to address this issue, adapting…

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

Large language models (LLMs) are in need of sufficient contexts to handle many critical applications, such as retrieval augmented generation and few-shot learning. However, due to the constrained window size, the LLMs can only access to the…

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

Recent studies show that in supervised fine-tuning (SFT) of large language models (LLMs), data quality matters more than quantity. While most data cleaning methods concentrate on filtering entire samples, the quality of individual tokens…

Large Language Models (LLMs) are increasingly applied to data-intensive workflows, from database querying to developer observability. Yet the effectiveness of these systems is constrained by the volume, verbosity, and noise of real-world…

The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively…

Subword tokenization has become the de-facto standard for tokenization, although comparative evaluations of subword vocabulary quality across languages are scarce. Existing evaluation studies focus on the effect of a tokenization algorithm…

Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current…

Tokenization strategies shape how models process electronic health records, yet fair comparisons of their effectiveness remain limited. We present a systematic evaluation of tokenization approaches for clinical time series modeling using…

This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing whether they capture genuine morphological structure or rely on surface…

Recent advancements in large language models(LLMs), such as GPT-4 and GPT-4o, have shown exceptional performance, especially in languages with abundant resources like English, thanks to extensive datasets that ensure robust training.…

Progress in pre-trained language models has led to a surge of impressive results on downstream tasks for natural language understanding. Recent work on probing pre-trained language models uncovered a wide range of linguistic properties…

Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token prediction training could contribute to this, because each…