Challenging the Abilities of Large Language Models in Italian: a Community Initiative

• URL: http://arxiv.org/abs/2512.04759v1
• Date: Thu, 04 Dec 2025 12:50:29 GMT
• Title: Challenging the Abilities of Large Language Models in Italian: a Community Initiative
• Abstract summary: "Challenging the Abilities of LAnguage Models in ITAlian" (CALAMITA) is a large-scale collaborative benchmarking initiative for Italian.<n>It federates more than 80 contributors from academia, industry, and the public sector to design, document, and evaluate a diverse collection of tasks.<n>We report results for four open-weight LLMs, highlighting systematic strengths and weaknesses across abilities.
• Score: 63.94242079171895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid progress of Large Language Models (LLMs) has transformed natural language processing and broadened its impact across research and society. Yet, systematic evaluation of these models, especially for languages beyond English, remains limited. "Challenging the Abilities of LAnguage Models in ITAlian" (CALAMITA) is a large-scale collaborative benchmarking initiative for Italian, coordinated under the Italian Association for Computational Linguistics. Unlike existing efforts that focus on leaderboards, CALAMITA foregrounds methodology: it federates more than 80 contributors from academia, industry, and the public sector to design, document, and evaluate a diverse collection of tasks, covering linguistic competence, commonsense reasoning, factual consistency, fairness, summarization, translation, and code generation. Through this process, we not only assembled a benchmark of over 20 tasks and almost 100 subtasks, but also established a centralized evaluation pipeline that supports heterogeneous datasets and metrics. We report results for four open-weight LLMs, highlighting systematic strengths and weaknesses across abilities, as well as challenges in task-specific evaluation. Beyond quantitative results, CALAMITA exposes methodological lessons: the necessity of fine-grained, task-representative metrics, the importance of harmonized pipelines, and the benefits and limitations of broad community engagement. CALAMITA is conceived as a rolling benchmark, enabling continuous integration of new tasks and models. This makes it both a resource -- the most comprehensive and diverse benchmark for Italian to date -- and a framework for sustainable, community-driven evaluation. We argue that this combination offers a blueprint for other languages and communities seeking inclusive and rigorous LLM evaluation practices.

Related papers

• Comprehensive Evaluation of Large Language Model Responses: A Multi-Factor Scoring System [0.0]
  This study introduces a multifactor scoring paradigm, integrating accuracy, conciseness, factual consistency, readability, and coherence.<n> Evaluations on the TruthfulQA dataset unveil mainstream LLMs' strengths in reasoning tasks.<n>This work carves a novel path for knowledge engineering and model refinement.
  arXiv  Detail & Related papers  (2026-07-08T03:10:33Z)
• OpenCompass: A Universal Evaluation Platform for Large Language Models [62.59671563145442]
  General-purpose large language models (LLMs) have become a critical link in advancing technological development.<n>Mainstream benchmark datasets face challenges such as the diversity of task types, inconsistent evaluation criteria, and fragmentation of data and processing.<n>This paper proposes and open-source Open LLMs, a one-stop, scalable, and high-concurrency general-purpose evaluation platform.
  arXiv  Detail & Related papers  (2026-05-19T02:50:11Z)
• SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures [93.36078244548077]
  The task data consist of an extended version of our manually constructed BLEnD benchmark (Myung et al. 2024), covering more than 30 language-culture pairs.<n>As the task is designed strictly for evaluation, participants were not permitted to use the data for training, fine-tuning, few-shot learning, or any other form of model modification.<n>We report the results and present an analysis of the best-performing systems and the most commonly adopted approaches.
  arXiv  Detail & Related papers  (2026-05-04T13:49:44Z)
• SemBench: A Universal Semantic Framework for LLM Evaluation [5.620203684062621]
  SemBench is a framework for automatically generating synthetic benchmarks that assess the semantic competence of Large Language Models (LLMs)<n>We evaluate SemBench in three languages (English, Spanish, and Basque) spanning different levels of linguistic resources.<n>Our results show that rankings derived from SemBench strongly correlate with those obtained from standard WiC datasets.
  arXiv  Detail & Related papers  (2026-03-12T08:56:13Z)
• Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models [1.175067374181304]
  Code-switching, the alternation of languages and scripts within a single utterance, remains a fundamental challenge for multilingual NLP.<n>Most large language models (LLMs) struggle with mixed-language inputs, limited CSW datasets, and evaluation biases.<n>This survey provides the first comprehensive analysis of CSW-aware LLM research.
  arXiv  Detail & Related papers  (2025-10-08T14:04:14Z)
• MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks [56.34018316319873]
  We propose MERA Code, a benchmark for evaluating code for the latest code generation LLMs in Russian.<n>This benchmark includes 11 evaluation tasks that span 8 programming languages.<n>We evaluate open LLMs and frontier API models, analyzing their limitations in terms of practical coding tasks in non-English languages.
  arXiv  Detail & Related papers  (2025-07-16T14:31:33Z)
• Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering [73.73820209993515]
  We introduce KoLasSimpleQA, the first benchmark evaluating the multilingual factual ability of Large Language Models (LLMs)<n>Inspired by existing research, we created the question set with features such as single knowledge point coverage, absolute objectivity, unique answers, and temporal stability.<n>Results show significant performance differences between the two domains.
  arXiv  Detail & Related papers  (2025-05-22T12:27:02Z)
• IberBench: LLM Evaluation on Iberian Languages [2.3034630097498883]
  Large Language Models (LLMs) are difficult to evaluate comprehensively, particularly for languages other than English.<n>We present IberBench, a benchmark designed to assess LLM performance on both fundamental and industry-relevant NLP tasks.<n>We evaluate 23 LLMs ranging from 100 million to 14 billion parameters and provide empirical insights into their strengths and limitations.
  arXiv  Detail & Related papers  (2025-04-23T17:48:25Z)
• Evalita-LLM: Benchmarking Large Language Models on Italian [3.3334839725239798]
  Evalita-LLM is a benchmark designed to evaluate Large Language Models (LLMs) on Italian tasks.<n>All tasks are native Italian, avoiding issues of translating from Italian and potential cultural biases.<n>The benchmark includes generative tasks, enabling more natural interaction with LLMs.
  arXiv  Detail & Related papers  (2025-02-04T12:58:19Z)
• All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages [73.93600813999306]
  ALM-bench is the largest and most comprehensive effort to date for evaluating LMMs across 100 languages.<n>It challenges existing models by testing their ability to understand and reason about culturally diverse images paired with text in various languages.<n>The benchmark offers a robust and nuanced evaluation framework featuring various question formats, including true/false, multiple choice, and open-ended questions.
  arXiv  Detail & Related papers  (2024-11-25T15:44:42Z)
• GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization [33.37163476772722]
  We aim to unify Multi-lingual, Cross-lingual and Multi-document Summarization into a novel task, i.e., MCMS, which encapsulates the real-world requirements all-in-one. We meticulously constructed the GLOBESUMM dataset by first collecting a wealth of multilingual news reports and restructuring them into event-centric format.
  arXiv  Detail & Related papers  (2024-10-05T08:56:44Z)
• Scalable Language Model with Generalized Continual Learning [58.700439919096155]
  The Joint Adaptive Re-ization (JARe) is integrated with Dynamic Task-related Knowledge Retrieval (DTKR) to enable adaptive adjustment of language models based on specific downstream tasks. Our method demonstrates state-of-the-art performance on diverse backbones and benchmarks, achieving effective continual learning in both full-set and few-shot scenarios with minimal forgetting.
  arXiv  Detail & Related papers  (2024-04-11T04:22:15Z)
• DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models [76.79929883963275]
  DIALIGHT is a toolkit for developing and evaluating multilingual Task-Oriented Dialogue (ToD) systems. It features a secure, user-friendly web interface for fine-grained human evaluation at both local utterance level and global dialogue level. Our evaluations reveal that while PLM fine-tuning leads to higher accuracy and coherence, LLM-based systems excel in producing diverse and likeable responses.
  arXiv  Detail & Related papers  (2024-01-04T11:27:48Z)
• Establishing Trustworthiness: Rethinking Tasks and Model Evaluation [36.329415036660535]
  We argue that it is time to rethink what constitutes tasks and model evaluation in NLP. We review existing compartmentalized approaches for understanding the origins of a model's functional capacity.
  arXiv  Detail & Related papers  (2023-10-09T06:32:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.