Large Language Models (LLMs) have been demonstrated to achieve state-of-art results on machine translation. LLM-based translation systems usually rely on model adaptation and fine-tuning, requiring datasets and compute. The goal of our team’s participation in the “General Machine Translation” and “Multilingual” tasks of WMT25 was to evaluate the translation effectiveness of a resource-efficient solution consisting of a smaller off-the-shelf LLM coupled with a self-refine agentic workflow. Our approach requires a high-quality multilingual LLM capable of instruction following. We select Gemma3-12B among several candidates using the pretrained translation metric MetricX-24 and a small development dataset. WMT25 automatic evaluations place our solution in the mid tier of all WMT25 systems, and also demonstrate that it can perform competitively for approximately 16% of language pairs.

Terminology-aware machine translation (MT) is needed in case of specialized domains such as science and law. Large Language Models (LLMs) have raised the level of state-of-art performance on the task of MT, but the problem is not completely solved, especially for use-cases requiring precise terminology translations. We participate in the WMT25 Terminology Translation Task with an LLM-based multi-agent system coupled with a custom terminology-aware translation quality metric for the selection of the final translation. We use a number of smaller open-weights LLMs embedded in an agentic “translation revision” workflow, and we do not rely on data- and compute-intensive fine-tuning of models. Our evaluations show that the system achieves very good results in terms of both MetricX-24 and a custom TSR metric designed to measure the adherence to predefined term mappings.

Large language models have recently risen in popularity due to their ability to perform many natural language tasks without requiring any fine-tuning. In this work, we focus on two novel ideas: (1) generating definitions from examples and using them for zero-shot classification, and (2) investigating how an LLM makes use of the definitions. We thoroughly analyze the performance of GPT-3 model for fine-grained multi-label conspiracy theory classification of tweets using zero-shot labeling. In doing so, we asses how to improve the labeling by providing minimal but meaningful context in the form of the definitions of the labels. We compare descriptive noun phrases, human-crafted definitions, introduce a new method to help the model generate definitions from examples, and propose a method to evaluate GPT-3’s understanding of the definitions. We demonstrate that improving definitions of class labels has a direct consequence on the downstream classification results.

What is the relation between a word and its description, or a word and its embedding? Both descriptions and embeddings are semantic representations of words. But, what information from the original word remains in these representations? Or more importantly, which information about a word do these two representations share? Definition Modeling and Reverse Dictionary are two opposite learning tasks that address these questions. The goal of the Definition Modeling task is to investigate the power of information laying inside a word embedding to express the meaning of the word in a humanly understandable way – as a dictionary definition. Conversely, the Reverse Dictionary task explores the ability to predict word embeddings directly from its definition. In this paper, by tackling these two tasks, we are exploring the relationship between words and their semantic representations. We present our findings based on the descriptive, exploratory, and predictive data analysis conducted on the CODWOE dataset. We give a detailed overview of the systems that we designed for Definition Modeling and Reverse Dictionary tasks, and that achieved top scores on SemEval-2022 CODWOE challenge in several subtasks. We hope that our experimental results concerning the predictive models and the data analyses we provide will prove useful in future explorations of word representations and their relationships.