Jul 2026· 2026 6th International Conference on Intelligent Communications and Computing (ICICC)· pp. 300-305· 0 citations· 23 references
Abstract
Large Language Models (LLMs) have significantly reshaped natural language processing by demonstrating strong capabilities in modeling long-range dependencies, capturing contextual semantics, and generating coherent natural language across a wide range of tasks. However, their performance often degrades when applied to specialized or low-resource domains, primarily due to domain shift and the presence of domainspecific terminology and knowledge. In addition, adapting LLMs to evolving domain requirements often incurs substantial computational costs. These limitations raise challenges in terms of reliability and contextual fidelity in real-world applications. This study presents a comprehensive overview of domain adaptation of Large Language Models and examines existing methods, with the objective of improving their accuracy, robustness, and effectiveness in specialized application settings.
Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating both pre-training corpora and evaluation suites. The recently released PolyMath (Wang et al., 2025) dataset represents a significant step forward, yet its coverage is still limited to 18 only high-resource languages. To address this gap, we introduce PluraMath, an extension of PolyMath to 18 additional {underrepresented languages spanning 6 language families -- ranging from mid-resource to extreme low-resource settings. We constructed the dataset through a human-curated pipeline, where native speakers thoroughly validated pre-computed translations. Using PluraMath, we then benchmark 27 reasoning LLMs across four model scales -- small, mid-size, large, and closed-source ensembles -- probing the multilingual mathematical reasoning capabilities of state-of-the-art models under diverse linguistic conditions. Our fine-grained analysis confirms a persistent gap in mathematical reasoning performance between high-resource and underrepresented languages, with stronger results largely associated with better instruction-following ability. We fully open-source our dataset, data acquisition pipeline, and evaluation framework, with the goal of lowering the barrier to multilingual benchmark development for underrepresented communities.
Daryna Dementieva, N. Babakov, Kathy Hammerl et al.· 0 citations
While Large Language Models (LLMs) show great promise for personalization, they often lack specialized domain knowledge. Conventional solutions like fine-tuning struggle with high computational costs and rapid data updates, while Retrieval-Augmented Generation fails to provide fine-grained, token-level steering. Furthermore, chat-based interfaces remain dominant, whereas productive co-writing paradigms have not yet been well exploited beyond the coding domain. To this end, we introduce SteerWrite, a training-free framework designed for personalized co-writing. Our method effectively adapts the base model to specialized domains without gradient updates, with specific designs tailored to small datasets. Experiments demonstrate that SteerWrite achieves state-of-the-art performance across diverse datasets, metrics, and models, significantly reducing human editing effort.
Wenhao Mao, Chengbin Hou, Weixiao Wang et al.· 0 citations
This study explores a semantic variation methodology to augment training data by generating question-answer pairs with explicit control over semantic similarity, and shows that semantically controlled augmentation improves domain-specific knowledge acquisition while preserving consistency.
Alexander Chen, Caroline Tang, Jennifer Sleeman· 0 citations
A methodical investigation of temporal prompting techniques for LLM-based EL is presented, and it is demonstrated that explicit temporal prompting can reduce drift mistakes by up to 40% using a dataset of temporally-sensitive mentions linked with Wikidata snapshots.
This systematic review examines recent progress in the pretraining and adaptation of LLMs for Low-Resource Languages (LRLs) and focuses on the ethics in AI practice, the development of corpora through communities, and interdisciplinary research collaboration among computational linguists, social scientists, and digital humanists.
Ismail Hossain, Mridul Banik, Fahmid Al Farid et al.· Computer Modeling in Enginee...· 0 citations
Abstract-Recently, large language models (LLMs) have enabled significant advances across a wide range of domains. However, the training, adaptation, and evaluation of LLMs with a large number of parameters incur substantial computational and financial costs. This limits the ability of researchers with constrained resources to effectively leverage LLM-based approaches. In this study, we examine the performance of relatively small-scale LLMs for question answering and retrieval-augmented generation (RAG) on Turkish legal texts under limited computational resources. We investigate several factors affecting Turkish RAG performance and adapt embedding models to the target domain using automatically generated question-context pairs. The findings indicate that relatively small, domain-adapted models can achieve performance levels close to those of larger-scale or commercial models on the target dataset.
Osman Büyük, Mustafa Erden· Signal Processing and Commun...· 0 citations