Reading Between the Tokens: Uncovering the Semantic Minima of AI Monologues
Invited talk at the CLCG Linguistics Lunch on identifying the load-bearing tokens in LLM Chain-of-Thought reasoning.
Apr 24, 2026
A Dialectic Pipeline for Improving LLM Robustness
A multi-agent self-dialogue pipeline for reducing hallucinations in LLMs without fine-tuning or domain-specific verifiers.
Jan 28, 2026
Large Language Models: Potenzialità, Limiti e Sistemi Multi-Agent
An industry-facing workshop on LLMs, multi-agent systems, and fine-tuning for businesses, co-organized with IP4FVG and the University of Trieste.
Dec 15, 2025
Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers
We present a Transformer-based approach to decode STL embeddings, enabling interpretable and semantically accurate formula generation, with applications to requirement mining.
Jul 10, 2025
OverRef: Studying Over-Refusal in Large Language Models
An ongoing research project investigating over-refusal behaviour in LLMs — when models refuse legitimate queries — and how to measure and mitigate it.
Jan 1, 2025