In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting expert specialization. We show that contrasting each token against an Exponential Moving Average of the layer’s hidden states, rather than routing on absolute magnitude, concentrates the routing signal onto a low-dimensional, highly separable subspace. Building on this, we propose the Contrastive Routing Mechanism (CoRM), which scores each expert by the gap between its affinity for the incoming token and its affinity for this shared reference state, interpreted through a distinct per-expert projection. The resulting experts have routing boundaries that align with linguistic structure significantly more than the Top-k baseline. Our experiments show that CoRM improves average zero-shot accuracy by +0.67 to +1.69 points (Top-1) and +1.38 to +1.77 points (Top-2) over standard Top-k MoE baselines on nine zero-shot reasoning benchmarks, at the minimal cost of 2.9% added parameters and 2.6% added FLOPs per token.

This paper presents the first automatic speech recognition (ASR) system for Cypriot Greek, a non-standardized variety of Modern Greek with distinctive phonological, lexical, and orthographic characteristics. We adapt Whisper, a state-of-the-art multilingual ASR model, to Cypriot Greek through fine-tuning on the mozilla common voice spontaneous speech dataset for Cypriot Greek. The phonological and lexical divergence of Cypriot Greek from Standard Modern Greek poses significant challenges for mainstream ASR, particularly under conditions of limited training data and dialectal variation. Results demonstrate that whisper-medium achieved a best word error rate (WER) of 37.85%, while whisper-large-v3 consistently outperformed it, reaching a minimum WER of 33.93%. In the light of these findings, increased model size, combined with targeted fine-tuning on normalized dialectical data, significantly improves recognition accuracy, indicating that careful handling of orthographic and dialectical variation provides an effective path for ASR adaptation to low-resource varieties.

We introduce Llama-Krikri-8B, a cutting-edge Large Language Model tailored for the Greek language, built on Meta’s Llama 3.1-8B. Llama-Krikri-8B has been extensively trained on high-quality Greek data to ensure superior adaptation to linguistic nuances. With 8 billion parameters, it offers advanced capabilities while maintaining efficient computational performance. Llama-Krikri-8B supports both Modern Greek and English, and is also equipped to handle polytonic text and Ancient Greek. The chat version of Llama-Krikri-8B features a multi-stage post-training pipeline, utilizing both human and synthetic instruction and preference data, by applying techniques such as MAGPIE. In addition, for evaluation, we propose three novel public benchmarks for Greek. Our evaluation on existing as well as the proposed benchmarks shows notable improvements over comparable Greek and multilingual LLMs in both natural language understanding and generation as well as code generation.

This paper presents SciPar, a new collection of parallel corpora created from openly available metadata of bachelor theses, master theses and doctoral dissertations hosted in institutional repositories, digital libraries of universities and national archives. We describe first how we harvested and processed metadata from 86, mainly European, repositories to extract bilingual titles and abstracts, and then how we mined high quality sentence pairs in a wide range of scientific areas and sub-disciplines. In total, the resource includes 9.17 million segment alignments in 31 language pairs and is publicly available via the ELRC-SHARE repository. The bilingual corpora in this collection could prove valuable in various applications, such as cross-lingual plagiarism detection or adapting Machine Translation systems for the translation of scientific texts and academic writing in general, especially for language pairs which include English.

Conversational Agents (CAs) can be a proxy for disseminating information and providing support to the public, especially in times of crisis. CAs can scale to reach larger numbers of end-users than human operators, while they can offer information interactively and engagingly. In this work, we present Theano, a Greek-speaking virtual assistant for COVID-19. Theano presents users with COVID-19 statistics and facts and informs users about the best health practices as well as the latest COVID-19 related guidelines. Additionally, Theano provides support to end-users by helping them self-assess their symptoms and redirecting them to first-line health workers. The relevant, localized information that Theano provides, makes it a valuable tool for combating COVID-19 in Greece. Theano has already conversed with different users in more than 170 different conversations through a web interface as a chatbot and over the phone as a voice bot.