Related papers: Racka: Efficient Hungarian LLM Adaptation on Acade…

Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context…

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with…

Despite significant advances in foundation models like DeepSeek-R1 and ChatGPT, their deployment in medical settings faces critical challenges including computational requirements and professional knowledge barriers. This paper presents an…

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning method for large language models, with its effectiveness largely influenced by the allocation of ranks and scaling factors, as well as initialization.…

Long text classification is challenging for Large Language Models (LLMs) due to token limits and high computational costs. This study explores whether a Retrieval Augmented Generation (RAG) approach using only the most relevant text…

The capabilities of Large Language Models (LLMs) in low-resource languages lag far behind those in English, making their universal accessibility a significant challenge. To alleviate this, we present $\textit{Franken-Adapter}$, a modular…

Tokenization remains a fundamental yet underexplored bottleneck in natural language processing, with strategies largely static despite remarkable progress in model architectures. We present SupraTok, a novel tokenization architecture that…

We present an extended comparison of contextualized language models for Hungarian. We compare huBERT, a Hungarian model against 4 multilingual models including the multilingual BERT model. We evaluate these models through three tasks,…

Large language models are trained with tokenizers, and the resulting token distribution is highly imbalanced: a few words dominate the stream while most occur rarely. Recent practice favors ever-larger vocabularies, but it is unclear where…

Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of…

While model architecture and training objectives are well-studied, tokenization, particularly in multilingual contexts, remains a relatively neglected aspect of Large Language Model (LLM) development. Existing tokenizers often exhibit high…

Low-rank adaptation (LoRA) is a natural method for finetuning in communication-constrained machine learning settings such as cross-device federated learning. Prior work that has studied LoRA in the context of federated learning has focused…

The advent of large language models (LLMs) has revolutionized natural language processing, enabling unprecedented capabilities in understanding and generating human-like text. However, the computational cost and convergence times associated…

We present two multilingual LLMs, Teuken 7B-base and Teuken 7B-instruct, designed to embrace Europe's linguistic diversity by supporting all 24 official languages of the European Union. Trained on a dataset comprising around 60% non-English…

Question answering (QA) models have shown rapid progress enabled by the availability of large, high-quality benchmark datasets. Such annotated datasets are difficult and costly to collect, and rarely exist in languages other than English,…

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…

We present the first comprehensive study of latent multi-head attention (MLA) for small language models, revealing interesting efficiency-quality trade-offs. Training 30M-parameter GPT models on 100,000 synthetic stories, we benchmark three…

Previous language model pre-training methods have uniformly applied a next-token prediction loss to all training tokens. Challenging this norm, we posit that "9l training". Our initial analysis examines token-level training dynamics of…

In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks. However, many mainstream LLMs (e.g. LLaMA) are…

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…