Kenneth D. Forbus

Learning Qualitative Models by Demonstration

Proceedings of the AAAI Conference on Artificial Intelligence · 2021 · 11 citations

Creating software agents that learn interactively requires the ability to learn from a small number of trials, extracting general, flexible knowledge that can drive behavior from observation and interaction. We claim that qualitative models provide a useful intermediate level of causal representation for dynamic domains, including the formulation of strategies and tactics. We argue that qualitative models are quickly learnable, and enable model-based reasoning techniques to be used to recognize,…

Same/different in visual reasoning

Current Opinion in Behavioral Sciences · 2020 · 7 citations

Analogical Reasoning, Generalization, and Rule Learning for Common Law Reasoning

2023-06-19 · 4 citations

Research in AI & Law has sought to model common-law case-based reasoning by creating analogies from cases, extracting and applying rules from cases, or both. This paper presents a new approach to extracting legal information from cases and several methods to apply it to new cases, including by analogy and by conversion to logical rules. It evaluates the approaches on a dataset of real-world cases and compares the results to off-the-shelf machine-learning techniques. We conclude that abstract leg…

The Illinois Intentional Tort Qualitative Dataset

Frontiers in artificial intelligence and applications · 2022-12-05 · 3 citations

We introduce the Illinois Intentional Tort Qualitative Dataset, a set of Illinois Common Law cases in Assault, Battery, Trespass, and Self-Defense, machine-translated into qualitative predicate representations. We discuss the cases involved, the natural language understanding system used to translate the cases into predicate logic, and validation measures that serve as performance baselines for future AI research using the dataset.

Using Large Language Models in the Companion Cognitive Architecture: A Case Study and Future Prospects

Proceedings of the AAAI Symposium Series · 2024-01-22 · 2 citations

The goal of the Companion cognitive architecture is to understand how to create human-like software social organisms. Thus natural language capabilities, both for reading and conversation, are essential. Recently we have begun experimenting with large language models as a component in the Companion architecture. This paper summarizes a case study indicating why we are currently using BERT with our symbolic natural language understanding system. It also describes some additional ways we are conte…