Eliana Pastor


2025

pdf bib
Privacy Preserving Data Selection for Bias Mitigation in Speech Models
Alkis Koudounas | Eliana Pastor | Vittorio Mazzia | Manuel Giollo | Thomas Gueudre | Elisa Reale | Luca Cagliero | Sandro Cumani | Luca De Alfaro | Elena Baralis | Daniele Amberti
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)

Effectively selecting data from subgroups where a model performs poorly is crucial for improving its performance. Traditional methods for identifying these subgroups often rely on sensitive information, raising privacy issues. Additionally, gathering such information at runtime might be impractical. This paper introduces a cost-effective strategy that addresses these concerns. We identify underperforming subgroups and train a model to predict if an utterance belongs to these subgroups without needing sensitive information. This model helps mitigate bias by selecting and adding new data, which is labeled as challenging, for re-training the speech model. Experimental results on intent classification and automatic speech recognition tasks show the effectiveness of our approach in reducing biases and enhancing performance, with improvements in reducing error rates of up to 39% for FSC, 16% for ITALIC, and 22% for LibriSpeech.

pdf bib
Detecting and Mitigating Challenges in Zero-Shot Video Summarization with Video LLMs
Luca Cagliero | Lorenzo Vaiani | Eliana Pastor | Alkis Koudounas | Elena Baralis | Vittorio Mazzia | Sandro Pollastrini | Thomas Gueudre | Manuel Giollo | Daniele Amberti | Yue Wu
Findings of the Association for Computational Linguistics: ACL 2025

Video summarization aims to generate a condensed textual version of an original video. Summaries may consist of either plain text or a shortlist of salient events, possibly including temporal or spatial references. Video Large Language Models (VLLMs) exhibit impressive zero-shot capabilities in video analysis. However, their performance varies significantly according to the LLM prompt, the characteristics of the video, and the properties of the training data and LLM architecture.In this work, we thoroughly evaluate the zero-shot summarization performance of four state-of-the-art open-source VLLMs specifically designed to address spatial and temporal reasoning. In light of the detected summarization issues, we propose different cost-effective mitigation strategies, based on Chain-of-Thought prompting, that involve the injection of knowledge extracted by external, lightweight models. To perform the VLLM evaluation, we design a new video summarization benchmark consisting of 100 videos with varying characteristics in terms of domain, duration, and spatio-temporal properties. Videos are manually annotated by three independent human experts with plain text, event-based, and spatio-temporal summaries. The experimental evaluation shows that VLLMs significantly benefit from prompting a list of recognized actions, whereas injecting automatically recognized objects and scene changes respectively improve spatially contextualized and event-based summaries in specific cases.

2024

pdf bib
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features
Eliana Pastor | Alkis Koudounas | Giuseppe Attanasio | Dirk Hovy | Elena Baralis
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

Predictive models make mistakes and have biases. To combat both, we need to understand their predictions.Explainable AI (XAI) provides insights into models for vision, language, and tabular data. However, only a few approaches exist for speech classification models. Previous works focus on a selection of spoken language understanding (SLU) tasks, and most users find their explanations challenging to interpret.We propose a novel approach to explain speech classification models. It provides two types of insights. (i) Word-level. We measure the impact of each audio segment aligned with a word on the outcome. (ii) Paralinguistic. We evaluate how non-linguistic features (e.g., prosody and background noise) affect the outcome if perturbed.We validate our approach by explaining two state-of-the-art SLU models on two tasks in English and Italian. We test their plausibility with human subject ratings. Our results show that the explanations correctly represent the model’s inner workings and are plausible to humans.

pdf bib
MAINDZ at SemEval-2024 Task 5: CLUEDO - Choosing Legal oUtcome by Explaining Decision through Oversight
Irene Benedetto | Alkis Koudounas | Lorenzo Vaiani | Eliana Pastor | Luca Cagliero | Francesco Tarasconi
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)

Large language models (LLMs) have recently obtained strong performance on complex reasoning tasks. However, their capabilities in specialized domains like law remain relatively unexplored. We present CLUEDO, a system to tackle a novel legal reasoning task that involves determining if a provided answer correctly addresses a legal question derived from U.S. civil procedure cases. CLUEDO utilizes multiple collaborator models that are trained using multiple-choice prompting to choose the right label and generate explanations. These collaborators are overseen by a final “detective” model that identifies the most accurate answer in a zero-shot manner. Our approach achieves an F1 macro score of 0.74 on the development set and 0.76 on the test set, outperforming individual models. Unlike the powerful GPT-4, CLUEDO provides more stable predictions thanks to the ensemble approach. Our results showcase the promise of tailored frameworks to enhance legal reasoning capabilities in LLMs.

2023

pdf bib
ferret: a Framework for Benchmarking Explainers on Transformers
Giuseppe Attanasio | Eliana Pastor | Chiara Di Bonaventura | Debora Nozza
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations

As Transformers are increasingly relied upon to solve complex NLP problems, there is an increased need for their decisions to be humanly interpretable. While several explainable AI (XAI) techniques for interpreting the outputs of transformer-based models have been proposed, there is still a lack of easy access to using and comparing them. We introduce ferret, a Python library to simplify the use and comparisons of XAI methods on transformer-based classifiers. With ferret, users can visualize and compare transformers-based models output explanations using state-of-the-art XAI methods on any free-text or existing XAI corpora. Moreover, users can also evaluate ad-hoc XAI metrics to select the most faithful and plausible explanations. To align with the recently consolidated process of sharing and using transformers-based models from Hugging Face, ferret interfaces directly with its Python library. In this paper, we showcase ferret to benchmark XAI methods used on transformers for sentiment analysis and hate speech detection. We show how specific methods provide consistently better explanations and are preferable in the context of transformer models.

pdf bib
PoliToHFI at SemEval-2023 Task 6: Leveraging Entity-Aware and Hierarchical Transformers For Legal Entity Recognition and Court Judgment Prediction
Irene Benedetto | Alkis Koudounas | Lorenzo Vaiani | Eliana Pastor | Elena Baralis | Luca Cagliero | Francesco Tarasconi
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

The use of Natural Language Processing techniques in the legal domain has become established for supporting attorneys and domain experts in content retrieval and decision-making. However, understanding the legal text poses relevant challenges in the recognition of domain-specific entities and the adaptation and explanation of predictive models. This paper addresses the Legal Entity Name Recognition (L-NER) and Court judgment Prediction (CPJ) and Explanation (CJPE) tasks. The L-NER solution explores the use of various transformer-based models, including an entity-aware method attending domain-specific entities. The CJPE proposed method relies on hierarchical BERT-based classifiers combined with local input attribution explainers. We propose a broad comparison of eXplainable AI methodologies along with a novel approach based on NER. For the L-NER task, the experimental results remark on the importance of domain-specific pre-training. For CJP our lightweight solution shows performance in line with existing approaches, and our NER-boosted explanations show promising CJPE results in terms of the conciseness of the prediction explanations.

2022

pdf bib
Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
Giuseppe Attanasio | Debora Nozza | Eliana Pastor | Dirk Hovy
Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP

Transformer-based Natural Language Processing models have become the standard for hate speech detection. However, the unconscious use of these techniques for such a critical task comes with negative consequences. Various works have demonstrated that hate speech classifiers are biased. These findings have prompted efforts to explain classifiers, mainly using attribution methods. In this paper, we provide the first benchmark study of interpretability approaches for hate speech detection. We cover four post-hoc token attribution approaches to explain the predictions of Transformer-based misogyny classifiers in English and Italian. Further, we compare generated attributions to attention analysis. We find that only two algorithms provide faithful explanations aligned with human expectations. Gradient-based methods and attention, however, show inconsistent outputs, making their value for explanations questionable for hate speech detection tasks.