Papers by Fabio Casati
BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models (2025.emnlp-main)
Copied to clipboard
Zsolt T. Kardkovács, Lynda Djennane, Anna Field, Boualem Benatallah, Yacine Gaci, Fabio Casati, Walid Gaaloul
| Challenge: | Sentiment Analysis (SA) models harbor inherent social biases that can be harmful in real-world applications. |
| Approach: | They propose a bias testing framework that generates high-quality test cases using Large Language Models (LLMs) for the controllable generation of test sentences. |
| Outcome: | The proposed framework generates high-quality test cases for bias testing in SA models with minimal specification using Large Language Models (LLMs) for the controllable generation of test sentences. |
Controllable Clustering with LLM-driven Embeddings (2025.emnlp-industry)
Copied to clipboard
Kerria Pang-Naylor, Shivani Manivasagan, Aitong Zhong, Mehak Garg, Nicholas Mondello, Blake Buckner, Jonathan P. Chang, Khyati Mahajan, Masoud Hashemi, Fabio Casati
| Challenge: | Unsupervised text clustering is unlikely to produce groupings that work across use cases . authors present techniques to effectively control text embeddings with minimal human input . |
| Approach: | They propose techniques to control text embeddings with minimal human input . they evaluate clustering performance for datasets with multiple independent labels . |
| Outcome: | The proposed techniques improve clustering for one perspective or use case, but at a tradeoff in performance for another use case. |
Debiasing Pretrained Text Encoders by Paying Attention to Paying Attention (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has exposed text encoders for replicating discriminatory social biases which may cause unintended and undesired model behaviors with respect to social groups. |
| Approach: | They propose a method to reduce social stereotypes by redistributing attention scores of a text encoder so it forgets any preference to historically advantaged groups and attends to all social classes with the same intensity. |
| Outcome: | The proposed method reduces stereotypes and inflicts no semantic damage on pre-trained encoders. |
Conceptual Similarity for Subjective Tags (2022.findings-aacl)
Copied to clipboard
| Challenge: | Existing methods of matching user queries with subjective tags rely on cosine similarity or semantic similarity models fail to recognize conceptual connections between tags. |
| Approach: | They propose a conceptual similarity pipeline to leverage conceptual awareness when assessing similarity between tags. |
| Outcome: | The proposed pipeline generates high-quality datasets and evaluates the model on a downstream application. |