103 citations · 272 across the 64 of their papers we have counts for
11 papers · 1 filter
Is Complex Query Answering Really Complex?
Cosimo Gregucci, Bo Xiong, Daniel Hernandez +4
Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be…
Logically Consistent Language Models via Neuro-Symbolic Integration
Diego Calanzone, Stefano Teso, Antonio Vergari
Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-…
What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?
Lorenzo Loconte, Antonio Mari, Gennaro Gala +5
This paper establishes a rigorous connection between circuit representations and tensor factorizations, two seemingly distinct yet fundamentally related areas. By connecting these…
Sum of Squares Circuits
Lorenzo Loconte, Stefan Mengel, Antonio Vergari
Designing expressive generative models that support exact and efficient inference is a core question in probabilistic ML. Probabilistic circuits (PCs) offer a framework where this…
What can Large Language Models Capture about Code Functional Equivalence?
Nickil Maveli, Antonio Vergari, Shay B. Cohen
Code-LLMs, LLMs pre-trained on large code corpora, have shown great progress in learning rich representations of the structure and syntax of code, successfully using it to generate…
A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
Samuele Bortolotti, Emanuele Marconato, Tommaso Carraro +5
The advent of powerful neural classifiers has increased interest in problems that require both learning and reasoning. These problems are critical for understanding important prope…
Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits
Gennaro Gala, Cassio de Campos, Antonio Vergari +1
Probabilistic integral circuits (PICs) have been recently introduced as probabilistic models enjoying the key ingredient behind expressive generative models: continuous latent vari…
Towards Logically Consistent Language Models via Probabilistic Reasoning
Diego Calanzone, Stefano Teso, Antonio Vergari
Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate…
On the Independence Assumption in Neurosymbolic Learning
Emile van Krieken, Pasquale Minervini, Edoardo M. Ponti +1
State-of-the-art neurosymbolic learning systems use probabilistic reasoning to guide neural networks towards predictions that conform to logical constraints over symbols. Many such…
PIXAR: Auto-Regressive Language Modeling in Pixel Space
Yintao Tai, Xiyang Liao, Alessandro Suglia +1
Recent work showed the possibility of building open-vocabulary large language models (LLMs) that directly operate on pixel representations. These models are implemented as autoenco…
BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
Emanuele Marconato, Samuele Bortolotti, Emile van Krieken +3
Neuro-Symbolic (NeSy) predictors that conform to symbolic knowledge - encoding, e.g., safety constraints - can be affected by Reasoning Shortcuts (RSs): They learn concepts consist…