7 papers
Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models
Sara Candussio, Daniel Scalena, Luca Bortolussi +3
Entropy-based pruning has been proposed as an effective method for compressing Chain-of-Thought (CoT) reasoning with negligible accuracy loss. We test the robustness of low- and hi…
"Don't Say It!": Constraints, Compliance, and Communication when Language Models Play Taboo
Sara Candussio, Francesca Padovani, Daniel Scalena +1
The game of Taboo requires describing a target word without using a set of forbidden words, so that other players can guess it. This deceptively simple task combines strict lexical…
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
Daniel Scalena, Sara Candussio, Luca Bortolussi +3
Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individual steps on the final answer poorly und…
RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue
Sara Candussio, Emanuele Ballarin, Lorenzo Bonin +2
The original Turing Test asks a human judge to distinguish a machine from a person through dialogue. Three quarters of a century later, conversational systems pass this test in cas…
Distilling Formal Logic into Neural Spaces: A Kernel Alignment Approach for Signal Temporal Logic
Sara Candussio, Gabriele Sarti, Gaia Saveri +1
We introduce a framework for learning continuous neural representations of formal specifications by distilling the geometry of their semantics into a latent space. Existing approac…
A Dialectic Pipeline for Improving LLM Robustness
Sara Candussio
Assessing ways in which Language Models can reduce their hallucinations and improve the outputs' quality is crucial to ensure their large-scale use. However, methods such as fine-t…