16 papers
Neuro-symbolic Weak Supervision: Theory and Semantics
Nijesh Upreti, Vaishak Belle
Weak supervision enables machine learning models to learn from limited or noisy labels, but it introduces challenges in reliability and semantic clarity, particularly in multi-inst…
Tractable Hierarchical Control of Autoregressive Language Models
Max Scribner, Antonio Vergari, Vaishak Belle
Constraining the generation of autoregressive large language models (LLMs) is an important component of integrating language models into formal systems. In the generation of code a…
A Counterfactual Cause in Situation Calculus
Daxin Liu, Vaishak Belle
Perhaps the most popular modern formulation of actual causality is the HP account by Halpern and Pearl. Recent advancement has focused on extension of HP account to lift its limite…
Integrating LTL Constraints into PPO for Safe Reinforcement Learning
Maifang Zhang, Hang Yu, Qian Zuo +3
This paper proposes Proximal Policy Optimization with Linear Temporal Logic Constraints (PPO-LTL), a framework that integrates safety constraints written in LTL into PPO for safe r…
Lyria: A Genetic Algorithm-Driven Neuro-Symbolic Reasoning Framework for LLMs
Weizhi Tang, Kwabena Nuamah, Vaishak Belle
While LLMs have demonstrated impressive abilities across various domains, they struggle with two major issues. The first is that LLMs trap themselves into local optima and the seco…
Propositional Abduction via Only-Knowing: A Non-Monotonic Approach
Sanderson Molick, Vaishak Belle
The paper introduces a basic logic of knowledge and abduction by extending Levesque logic of only-knowing with an abduction modal operator defined via the combination of basic epis…