publications

2026

1. 

   Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models

   Daniel Scalena^*, Sara Candussio^*, Luca Bortolussi, and 3 more authors

   2026

   Abs HTML PDF

   Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individual steps on the final answer poorly understood. We estimate each step’s causal importance via early exit and use this measure to study how answers form across the reasoning traces of several model families. Across diverse tasks, we find that reasoning typically crosses a commitment boundary – a sharp transition from transient intermediate guesses to a stable, high-confidence answer. This transition often happens in a single step, well before the model’s reasoning block ends, and is followed by epiphenomenal CoT steps that leave the final answer probability unaltered. Using attention probes, we show that answer-formation stages can be linearly decoded from intermediate reasoning steps with high accuracy and generalize robustly to unseen reasoning tasks. We exploit this signal to early-exit reasoning blocks at the commitment boundary, reducing the length of CoTs up to 55% on average with negligible impact on model performance.

2025

1. 

   EAGer: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling

   Daniel Scalena, Leonidas Zotos, Elisabetta Fersini, and 2 more authors

   2025

   Proceedings of the 43rd International Conference on Machine Learning, (ICML 2026)

   Abs HTML Poster

   With the rise of reasoning language models and test-time scaling methods as a paradigm for improving model performance, substantial computation is often required to generate multiple candidate sequences from the same prompt. This enables exploration of different reasoning paths toward the correct solution, however, allocates the same compute budget for each prompt. Grounded on the assumption that different prompts carry different degrees of complexity, and thus different computation needs, we propose EAGer, a training-free generation method that leverages model uncertainty through token-wise entropy distribution to reduce redundant computation and concurrently improve overall performance. EAGer allows branching to multiple reasoning paths only in the presence of high-entropy tokens, and then reallocates the saved compute budget to the instances where exploration of alternative paths is most needed. We find that across multiple open-source models on complex reasoning benchmarks such as AIME 2025, EAGer can reallocate the budget without accessing target labels, achieving the best efficiency-performance trade-off in terms of reasoning length and Pass@k. When target labels are accessible, EAGer generates up to 65% fewer tokens (hence saving compute) and achieves up to 37% improvement in Pass@k compared to the Full Parallel Sampling.

2. 

   Steering Large Language Models for Machine Translation Personalization

   Daniel Scalena^*, Gabriele Sarti^*, Arianna Bisazza, and 2 more authors

   2025

   Proceedings of the 19th Conference of the European Chapter of the Association for CL, (EACL 2026)

   Abs HTML

   High-quality machine translation systems based on large language models (LLMs) have simplified the production of personalized translations reflecting specific stylistic constraints. However, these systems still struggle in settings where stylistic requirements are less explicit and might be harder to convey via prompting. We explore various strategies for personalizing LLM-generated translations in low-resource settings, focusing on the challenging literary translation domain. We explore prompting strategies and inference-time interventions for steering model generations towards a personalized style, and propose a contrastive framework exploiting latent concepts extracted from sparse autoencoders to identify salient personalization properties. Our results show that steering achieves strong personalization while preserving translation quality. We further examine the impact of steering on LLM representations, finding model layers with a relevant impact for personalization are impacted similarly by multi-shot prompting and our steering method, suggesting similar mechanism at play.

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

   Malvina Nissim, Danilo Croce, Viviana Patti, and 4 more authors

   2025

   Abs HTML

   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 assembled a benchmark of over 20 tasks and almost 100 subtasks, and established a centralized evaluation pipeline that supports heterogeneous datasets and metrics. CALAMITA is conceived as a rolling benchmark, enabling continuous integration of new tasks and models, offering a blueprint for other languages and communities seeking inclusive and rigorous LLM evaluation practices.

4. Uncovering Unsafety Traits in Italian Language Models

   Giulia Rizzi, Giuseppe Magazzù, Alberto Sormani, and 3 more authors

   In Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025), Sep 2025

   Abs HTML PDF

   Large Language Models (LLMs) are increasingly deployed in real-world applications, raising urgent concerns around their safety, reliability, and ethical behavior. While existing safety evaluations have primarily focused on English, low- and mid-resource languages such as Italian remain critically underexplored. In this paper, we present the first comprehensive and multidimensional evaluation of LLM safety in the Italian language. We assess seven state-of-the-art LLMs across key safety dimensions using several automatic moderators tailored to cover the Italian settings. Furthermore, we analyze the challenges of adapting English-centric safety benchmarks to Italian via machine translation, highlighting limitations and proposing best practices for developing culturally and linguistically grounded evaluation frameworks.

5. BeaverTails-IT: Towards a Safety Benchmark for Evaluating Italian Large Language Models

   Giuseppe Magazzù, Alberto Sormani, Giulia Rizzi, and 7 more authors

   In Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025), Sep 2025

   Abs HTML PDF

   Large Language Models (LLMs) have achieved remarkable success in generating human-like text and are increasingly integrated into real-world applications. However, their deployment raises significant safety concerns, including the risk of generating harmful, biased, or culturally inappropriate content. While several safety benchmarks exist for English, non-English contexts—such as Italian—remain critically underexplored, despite the growing demand for localized and culturally sensitive AI technologies. In this paper, we introduce BeaverTails-IT, the first Italian safety benchmark for LLMs, created through the machine translation of the original English BeaverTails dataset. We employ five state-of-the-art translation models, evaluate translation quality using automated metrics and human judgments, and provide guidelines for selecting high-quality safety prompts. Our benchmark enables the preliminary evaluation of Italian LLMs across key safety dimensions such as toxicity, bias, and ethical compliance.

6. Gender Violence in Numbers: Prompting Italian LLMs to Characterize Crimes against Women

   Giulia Rizzi, Daniel Scalena, and Elisabetta Fersini

   In Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025), Sep 2025

   Abs HTML PDF

   This paper investigates the application of various prompting strategies and Italian-language large language models (LLMs) to extract salient characteristics of gender-based crimes from judicial courtroom decisions. Recognizing the complex linguistic and legal structures inherent in such documents, we evaluate several types of prompting across multiple LLMs fine-tuned or pretrained on Italian corpora. Our approach focuses on identifying key elements such as crime typology, victim-perpetrator relationships, modus operandi, and main motivations behind the crimes against women. We present a comparative analysis of LLM performance on a small set of judicial courtrooms, highlighting the impact of prompt design on the extraction of legally and socially relevant information. The findings demonstrate the potential of prompt engineering to enhance the ability of LLMs to support socio-legal research and policy development in the context of gender-based violence.

2024

1. 

   A Gentle Push Funziona Benissimo: Making Instructed Models in Italian via Contrastive Activation Steering

   Daniel Scalena, Elisabetta Fersini, and Malvina Nissim

   In Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024), Dec 2024

   Abs PDF

   Adapting models to a language that was only partially present in the pre-training data requires fine-tuning, which is expensive in terms of both data and computational resources. As an alternative to fine-tuning, we explore the potential of activation steering-based techniques to enhance model performance on Italian tasks. Through our experiments we show that Italian steering (i) can be successfully applied to different models, (ii) achieves performances comparable to, or even better than, fine-tuned models for Italian, and (iii) yields higher quality and consistency in Italian generations. We also discuss the utility of steering and fine-tuning in the contemporary LLM landscape where models are anyway getting high Italian performances even if not explicitly trained in this language.

2. 

   Multi-property Steering of Large Language Models with Dynamic Activation Composition

   Daniel Scalena, Gabriele Sarti, and Malvina Nissim

   In Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, Nov 2024

   Abs HTML PDF

   Activation steering methods were shown to be effective in conditioning language model generation by additively intervening over models’ intermediate representations. However, the evaluation of these techniques has so far been limited to single conditioning properties and synthetic settings. In this work, we conduct a comprehensive evaluation of various activation steering strategies, highlighting the property-dependent nature of optimal parameters to ensure a robust effect throughout generation. To address this issue, we propose Dynamic Activation Composition, an information-theoretic approach to modulate the steering intensity of one or more properties throughout generation. Our experiments on multi-property steering show that our method successfully maintains high conditioning while minimizing the impact of conditioning on generation fluency.

3. CALAMITA: Challenge the Abilities of LAnguage Models in ITAlian

   Giuseppe Attanasio, Pierpaolo Basile, Federico Borazio, and 8 more authors

   In Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024), Dec 2024

   Abs HTML PDF

   The rapid development of Large Language Models (LLMs) has called for robust benchmarks to assess their abilities, track progress, and compare iterations. While existing benchmarks provide extensive evaluations across diverse tasks, they predominantly focus on English, leaving other languages underserved. For Italian, the EVALITA campaigns have provided a long-standing tradition of classification-focused shared tasks. However, their scope does not fully align with the nuanced evaluation required for modern LLMs. To address this gap, we introduce “Challenge the Abilities of LAnguage Models in ITAlian” (CALAMITA), a collaborative effort to create a dynamic and growing benchmark tailored to Italian. CALAMITA emphasizes diversity in task design to test a wide range of LLM capabilities through resources natively developed in Italian by the community. This initiative includes a shared platform, live leaderboard, and centralized evaluation framework. This paper outlines the collaborative process, initial challenges, and evaluation framework of CALAMITA.

2023

1. 

   Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence

   Daniel Scalena, Gabriele Sarti, Malvina Nissim, and 1 more author

   Dec 2023

   Abs HTML PDF

   Due to language models’ propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users’ preferences. Despite the effectiveness of such methods in improving the safety of model interactions, their impact on models’ internal processes is still poorly understood. In this work, we apply popular detoxification approaches to several language models and quantify their impact on the resulting models’ prompt dependence using feature attribution methods. We evaluate the effectiveness of counter-narrative fine-tuning and compare it with reinforcement learning-driven detoxification, observing differences in prompt reliance between the two methods despite their similar detoxification performances.

2. 

   MIND at SemEval-2023 Task 11: From Uncertain Predictions to Subjective Disagreement

   Giulia Rizzi, Alessandro Astorino, Daniel Scalena, and 2 more authors

   In Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023), Jul 2023

   Abs HTML PDF

   This paper describes the participation of the research laboratory MIND, at the University of Milano-Bicocca, in the SemEval 2023 task related to Learning With Disagreements (Le-Wi-Di). The main goal is to identify the level of agreement/disagreement from a collection of textual datasets with different characteristics in terms of style, language and task.The proposed approach is grounded on the hypothesis that the disagreement between annotators could be grasped by the uncertainty that a model, based on several linguistic characteristics, could have on the prediction of a given gold label.

2021

1. Tecniche di Natural Language Processing per il riconoscimento dei discorsi d’odio sui social network

   Daniel Scalena

   Jul 2021

   HTML