AIConfPaper
← Search

Alessio Miaschi

8 accepted papers

2025

All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark

Davide Testa, Giovanni Bonetta, Raffaella Bernardi, Alessandro Bondielli, Alessandro Lenci, Alessio Miaschi +2
EMNLP 2025

We introduce MAIA (Multimodal AI Assessment), a native-Italian benchmark designed for fine-grained investigation of the reasoning abilities of visual language models on videos. MAIA differs from other available video benchmarks for its design, its reasoning categories, the metric it uses, and the la

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Beyond the Spelling Miracle: Investigating Substring Awareness in Character-Blind Language Models

Cristiano Ciaccio, Marta Sartor, Alessio Miaschi, Felice Dell’Orletta
ACL 2025finding

Correctly identifying characters and substrings of words should be a basic but essential ability of any Language Model that aims to proficiently understand and produce language. Despite so, the majority of Pre-trained Language Models (PLMs) are “character-blind” and struggle in spelling tasks, altho…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Evaluating Lexical Proficiency in Neural Language Models

Cristiano Ciaccio, Alessio Miaschi, Felice Dell’Orletta
ACL 2025long

We present a novel evaluation framework designed to assess the lexical proficiency and linguistic creativity of Transformer-based Language Models (LMs). We validate the framework by analyzing the performance of a set of LMs of different sizes, in both mono- and multilingual configuration, across tas…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation

Luca Moroni, Giovanni Puccetti, Pere-Lluís Huguet Cabot, Andrei Stefan Bejgu, Alessio Miaschi, Edoardo Barba +3
NAACL 2025findings

The number of pretrained Large Language Models (LLMs) is increasing steadily, though the majority are designed predominantly for the English language. While state-of-the-art LLMs can handle other languages, due to language contamination or some degree of multilingual pretraining data, they are not o…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2025

Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors

Andrea Pedrotti, Michele Papucci, Cristiano Ciaccio, Alessio Miaschi, Giovanni Puccetti, Felice Dell’Orletta +1
ACL 2025finding

Recent advancements in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation. Moreover, detecting Machine-Generated Text (MGT) remains challenging…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Evaluating Large Language Models via Linguistic Profiling

Alessio Miaschi, Felice Dell’Orletta, Giulia Venturi
EMNLP 2024main

Large Language Models (LLMs) undergo extensive evaluation against various benchmarks collected in established leaderboards to assess their performance across multiple tasks. However, to the best of our knowledge, there is a lack of comprehensive studies evaluating these models’ linguistic abilities…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It)

Alessio Miaschi, Felice Dell’Orletta, Giulia Venturi
COLING 2024main

In this paper, we explore the impact of augmenting pre-trained Encoder-Decoder models, specifically T5, with linguistic knowledge for the prediction of a target task. In particular, we investigate whether fine-tuning a T5 model on an intermediate task that predicts structural linguistic properties o…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2020

Linguistic Profiling of a Neural Language Model

Alessio Miaschi, Dominique Brunato, Felice Dell’Orletta, Giulia Venturi
COLING 2020main

In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set of probing tasks, each of which corresponds to a distinct sen…

Cited by 70Source ↗PDF ↗Scholar ↗