Papers by Davide Buscaldi
Unveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoders (2026.findings-eacl)
Copied to clipboard
| Challenge: | Concept-based explanations for large language models are not well understood in text classification. |
| Approach: | They propose a model with a specialized classifier head and activation rate sparsity loss for sentence classification . they compare it to existing models with HI-Concept and ConceptShap . |
| Outcome: | The proposed model improves both the causality and interpretability of the extracted features. |
A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications (2022.lrec-1)
Copied to clipboard
| Challenge: | Automated text generation has achieved performance levels that make the generated text almost indistinguishable from those written by humans. |
| Approach: | They propose to use a completely synthetic dataset and a partial text substitution dataset to evaluate the quality of the generated research content. |
| Outcome: | The proposed datasets compare the generated texts to aligned original texts using fluency metrics such as BLEU and ROUGE. |