Papers by Nicola Tonellotto
Statistical Foundations of DIME: Risk Estimation for Practical Index Selection (2026.eacl-short)
Copied to clipboard
Giulio D'Erasmo, Cesare Campagnano, Antonio Mallia, Pierpaolo Brutti, Nicola Tonellotto, Fabrizio Silvestri
| Challenge: | High-dimensional dense embeddings are noisy or redundant, causing performance degradation and causing errors. |
| Approach: | They propose a method that scores each dimension by fusing the embeddings into a query-dependent matrix. |
| Outcome: | The proposed method improves retrieval effectiveness and reduces embedding size by an average 50% of across different models and datasets at inference time. |
The Mechanics of Interference: Defusing Distractors in RAG via Sparse Autoencoder Interventions (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models exhibit a critical vulnerability to distractor interference when processing retrieval-augmented contexts. |
| Approach: | They propose a mechanistic framework that corrects this failure mode through targeted interventions in the model’s latent space. |
| Outcome: | The proposed framework achieves recovery rates of up to 94% on distractor-vulnerable samples on Gemma-2 and Llama-3 model families across three QA benchmarks. |