Related papers: Through the Looking Glass, and what Horn Clause Pr…
The integrity of AI benchmarks is fundamental to accurately assess the capabilities of AI systems. The internal validity of these benchmarks - i.e., making sure they are free from confounding factors - is crucial for ensuring that they are…
Answer Set Programming (ASP) is an important logic programming paradigm within the field of Knowledge Representation and Reasoning. As a concise, human-readable, declarative language, ASP is an excellent tool for developing trustworthy…
A definite Horn theory is a set of n-dimensional Boolean vectors whose characteristic function is expressible as a definite Horn formula, that is, as conjunction of definite Horn clauses. The class of definite Horn theories is known to be…
We present a method for automatic inference of conditions on the initial states of a program that guarantee that the safety assertions in the program are not violated. Constrained Horn clauses (CHCs) are used to model the program and…
We study how to subvert large language models (LLMs) from following prompt-specified rules. We first formalize rule-following as inference in propositional Horn logic, a mathematical system in which rules have the form "if $P$ and $Q$, then…
As large language models (LLMs) are increasing integrated into fact-checking pipelines, formal logic is often proposed as a rigorous means by which to mitigate bias, errors and hallucinations in these models' outputs. For example, some…
Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they are…
The work reported here introduces Defeasible Logic Programming (DeLP), a formalism that combines results of Logic Programming and Defeasible Argumentation. DeLP provides the possibility of representing information in the form of weak rules…
We demonstrate how AI agents can coordinate to deceive oversight systems using automated interpretability of neural networks. Using sparse autoencoders (SAEs) as our experimental framework, we show that language models (Llama, DeepSeek R1,…
The ability to explain decisions made by AI systems is highly sought after, especially in domains where human lives are at stake such as medicine or autonomous vehicles. While it is often possible to approximate the input-output relations…
This paper calls on the research community not only to investigate how human biases are inherited by large language models (LLMs) but also to explore how these biases in LLMs can be leveraged to make society's "unwritten code" - such as…
We introduce two-sided type systems, which are sequent calculi for typing formulas. Two-sided type systems allow for hypothetical reasoning over the typing of compound program expressions, and the refutation of typing formulas. By…
Across machine learning (ML) sub-disciplines researchers make mathematical assumptions to facilitate proof-writing. While such assumptions are necessary for providing mathematical guarantees for how algorithms behave, they also necessarily…
A new approach to the local and global explanation is proposed. It is based on selecting a convex hull constructed for the finite number of points around an explained instance. The convex hull allows us to consider a dual representation of…
Sophisticated machine models are increasingly used for high-stakes decisions in everyday life. There is an urgent need to develop effective explanation techniques for such automated decisions. Rule-Based Explanations have been proposed for…
In this paper we reexamine the place and role of stable model semantics in logic programming and contrast it with a least Herbrand model approach to Horn programs. We demonstrate that inherent features of stable model semantics naturally…
Experimental and observational studies often lack validity due to untestable assumptions. We propose a double machine learning approach to combine experimental and observational studies, allowing practitioners to test for assumption…
The fundamental problem of causal inference - that the counterfactual outcome for any individual is never observed - has shaped the entire methodology of the field. Every existing approach substitutes assumptions for missing data:…
Reasoning models frequently agree with incorrect user suggestions -- a behavior known as sycophancy. However, it is unclear where in the reasoning trace this agreement originates and how strong the commitment is. We introduce…
This paper examines a critical yet unexplored dimension of the AI alignment problem: the potential for Large Language Models (LLMs) to inherit and amplify existing misalignments between human espoused theories and theories-in-use. Drawing…