6 papers
Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models
Gabriele Maraia, Marco Valentino, Fabio Massimo Zanzotto +1
Large Language Models (LLMs) often struggle with deductive judgment in syllogistic reasoning, systematically conflating semantic plausibility with formal validity a phenomenon know…
Logic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning
Ali Farjami, Luca Redondi, Marco Valentino
Large language models (LLMs) and theorem provers (TPs) can be effectively combined for verifiable natural language inference (NLI). However, existing approaches rely on a fixed log…
Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition
Lei Xu, Pierre Beckmann, Marco Valentino +1
Neuro-symbolic NLP methods aim to leverage the complementary strengths of large language models and formal logical solvers. However, current approaches are mostly static in nature,…
How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion Models
Feng He, Zhenyang Liu, Marco Valentino +1
Model editing offers a low-cost technique to inject or correct a particular behavior in a pre-trained model without extensive retraining, supporting applications such as factual co…
Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
Yingji Zhang, Marco Valentino, Danilo S. Carvalho +1
Incorporating explicit reasoning rules within the latent space of language models (LMs) offers a promising pathway to enhance generalisation, interpretability, and controllability.…
Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision
Xingwei Tan, Marco Valentino, Mahmud Akhter +2
Large language models (LLMs) have shown strong performance in many reasoning benchmarks. However, recent studies have pointed to memorization, rather than generalization, as one of…