Related papers: Better AI through Logical Scaffolding
With the rapid advancement of AI, software engineering increasingly relies on AI-driven approaches, particularly language models (LMs), to enhance code performance. However, the trustworthiness and reliability of LMs remain significant…
Semi-structured interviews are a common method in qualitative research. However, conducting high-quality interviews is cognitively demanding and requires strong interviewing skills. To lower this bar, we propose InterFlow, an AI-powered…
Artificial Intelligence (AI) is being increasingly deployed in practical applications. However, there is a major concern whether AI systems will be trusted by humans. In order to establish trust in AI systems, there is a need for users to…
As AI becomes more deeply embedded in knowledge work, building assistants that support human creativity and expertise becomes more important. Yet achieving synergy in human-AI collaboration is not easy. Providing AI with detailed…
Assessments of algorithmic bias in large language models (LLMs) are generally catered to uncovering systemic discrimination based on protected characteristics such as sex and ethnicity. However, there are over 180 documented cognitive…
In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning translates high-level goals into smaller, executable steps that…
Tractable Boolean and arithmetic circuits have been studied extensively in AI for over two decades now. These circuits were initially proposed as "compiled objects," meant to facilitate logical and probabilistic reasoning, as they permit…
The need to explain the output from Machine Learning systems designed to predict the outcomes of legal cases has led to a renewed interest in the explanations offered by traditional AI and Law systems, especially those using factor based…
Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete challenges and assessing progress to…
Logic program transformation by the unfold/fold method ad- vocates the writing of correct logic programs via the application of some rules to a naive program. This work focuses on how to overcome subgoal- introduction difficulties in…
We propose a method for program generation based on semantic scaffolds, lightweight structures representing the high-level semantic and syntactic composition of a program. By first searching over plausible scaffolds then using these as…
This paper reviews the architecture and implementation methods of agents powered by large language models (LLMs). Motivated by the limitations of traditional LLMs in real-world tasks, the research aims to explore patterns to develop…
Work on "learning with rationales" shows that humans providing explanations to a machine learning system can improve the system's predictive accuracy. However, this work has not been connected to work in "explainable AI" which concerns…
Modern AI models contain much of human knowledge, yet understanding of their internal representation of this knowledge remains elusive. Characterizing the structure and properties of this representation will lead to improvements in model…
This paper illustrates how a Prolog program, using chronological backtracking to find a solution in some search space, can be enhanced to perform intelligent backtracking. The enhancement crucially relies on the impurity of Prolog that…
We report on several scenarios of using automated theorem proving software in university education. In particular, we focus on using the Theorema system in a software-enhanced logic-course for students in computer science or artificial…
The increasing prominence of AI necessitates the deployment of inference platforms for efficient and effective management of AI pipelines and compute resources. As these pipelines grow in complexity, the demand for distributed serving rises…
Cognitive studies and artificial intelligence have developed distinct models for various inferential mechanisms (categorization, induction, abduction, causal inference, contrast, merge, ...). Yet, both natural and artificial views on…
The most common methods in explainable artificial intelligence are post-hoc techniques which identify the most relevant features used by pretrained opaque models. Some of the most advanced post hoc methods can generate explanations that…
Artificial Intelligence systems cannot yet match human abilities to apply knowledge to situations that vary from what they have been programmed for, or trained for. In visual object recognition methods of inference exploiting top-down…