Alessio Miaschi's picture

Alessio Miaschi

alemiaschi

·

https://alemiaschi.github.io/

AI & ML interests

Analysis and interpretability of small- and large-scale LMs

Recent Activity

liked a dataset 4 days ago

swj0419/WikiMIA

liked a model 5 days ago

Fastweb/FastwebMIIA-7B

upvoted a paper 12 days ago

Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization

View all activity

Organizations

None yet

authored a paper 25 days ago

Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors

Paper • 2505.24523 • Published 29 days ago • 9

authored a paper 2 months ago

Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation

Paper • 2504.17025 • Published Apr 23 • 16

authored a paper 4 months ago

All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark

Paper • 2502.16989 • Published Feb 24

authored a paper 7 months ago

Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluation

Paper • 2412.07338 • Published Dec 10, 2024 • 2

authored 4 papers 11 months ago

Leveraging Large Language Models for Mobile App Review Feature Extraction

Paper • 2408.01063 • Published Aug 2, 2024

Linguistic Profiling of a Neural Language Model

Paper • 2010.01869 • Published Oct 5, 2020

T-FREX: A Transformer-based Feature Extraction Method from Mobile App Reviews

Paper • 2401.03833 • Published Jan 8, 2024

Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It)

Paper • 2402.17608 • Published Feb 27, 2024