Author

Luca Bortolussi

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jun 2026

Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models

This work uses answer logits at the end of each reasoning step to estimate each step's causal importance to the final answer and intermediate guesses, shedding light on the answer formation process of several reasoning model families.

Daniel Scalena, Sara Candussio, Luca Bortolussi et al. · arXiv.org · 3 citations

#natural language process... Jul 2026

Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models

It is demonstrated that patching a subset of a few CoT tokens with their original activations recovers near-perfect full-trace performance, providing causal evidence that task information is not concentrated in a small set of CoT tokens identifiable by heuristics, but rather distributed across the full reasoning chain.

Sara Candussio, Daniel Scalena, Luca Bortolussi et al. · arXiv.org · 0 citations