CATO is an intelligent learning environment designed to help beginning law students learn basic skills of making arguments with cases. Using CATO, students practice tasks of induction and analogical argumentation. They practice testing theories against a body of cases and making written arguments about a problem, comparing and contrasting it to past cases.
CATO's model addresses arguments in which two opponents analogize a problem to favorable cases, distinguish unfavorable cases, assess the significance of similarities and differences between cases in light of normative knowledge about the domain, and use that knowledge to organize multi-case arguments. CATO communicates the model to students by presenting dynamically-generated argumentation examples and by reifying argument structure based on the model. CATO also provides a case database and tools based on the model that help make students' tasks more manageable.
CATO was evaluated in the context of an actual legal writing course, in a study involving 30 first-year law students. We found that instruction with CATO leads to statistically significant improvement in students' basic argumentation skills, comparable to that achieved by an experienced legal writing instructor teaching groups of 4-10 students. However, on a more advanced legal writing assignment, meant to explore the frontier of the CATO instruction, students taught by the legal writing instructor had higher grades, suggesting a need for more integrated practice with the CATO model.
CATO contributes to AI research fields modeling educational techniques as well as case-based and legal reasoning. It is a novel result that students can learn basic argumentation skills by studying computer-generated examples. It means that an instructional system does not necessarily need to rely on a very sophisticated understanding of students' arguments, which would be a significant obstacle to developing such systems.
Also, CATO presents novel techniques for using background knowledge to support similarity assessment in case-based reasoning. Drawing on its background knowledge, CATO characterizes and re-characterizes cases in order to argue that two cases are similar or different. This is an important skill in the legal domain not previously modeled. CATO's arguments may help a user in assessing the similarity of cases in a more discriminatory way.
Cited By
- Rodríguez Rodríguez C, Amoroso Fernández Y, Zuev D, Peña Abreu M and Zulueta Veliz Y (2024). M-LAMAC: a model for linguistic assessment of mitigating and aggravating circumstances of criminal responsibility using computing with words, Artificial Intelligence and Law, 32:3, (697-739), Online publication date: 1-Sep-2024.
- Novotná T and Libal T An Evaluation of Methodologies for Legal Formalization Explainable and Transparent AI and Multi-Agent Systems, (189-203)
- Broughton G (2019). Vertical precedents in formal models of precedential constraint, Artificial Intelligence and Law, 27:3, (253-307), Online publication date: 1-Sep-2019.
- Branting K, Weiss B, Brown B, Pfeifer C, Chakraborty A, Ferro L, Pfaff M and Yeh A Semi-Supervised Methods for Explainable Legal Prediction Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law, (22-31)
- Atkinson K and Bench-Capon T Reasoning with Legal Cases Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law, (12-21)
- Al-Abdulkarim L, Atkinson K, Atkinson S and Bench-Capon T Angelic environment Proceedings of the 16th edition of the International Conference on Articial Intelligence and Law, (267-268)
- Araszkiewicz M, Łopatkiewicz A, Zienkiewicz A and Zurek T Representation of an actual divorce dispute in the parenting plan support system Proceedings of the 15th International Conference on Artificial Intelligence and Law, (166-170)
- Al-Abdulkarim L, Atkinson K and Bench-Capon T Evaluating the use of abstract dialectical frameworks to represent case law Proceedings of the 15th International Conference on Artificial Intelligence and Law, (156-160)
- Al-Abdulkarim L, Atkinson K and Bench-Capon T Factors, issues and values Proceedings of the 15th International Conference on Artificial Intelligence and Law, (3-12)
- Kubosawa S, Nishina K, Sugimoto M, Okada S and Nitta K A discussion training support system and its evaluation Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law, (197-201)
- Araszkiewicz M, Łopatkiewicz A and Zienkiewicz A Factor-based parent plan support system Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law, (171-175)
- Bench-Capon T, Prakken H, Wyner A and Atkinson K Argument schemes for reasoning with legal cases using values Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law, (13-22)
- Bench-Capon T Open texture and argumentation Logic Programs, Norms and Action, (220-233)
- Araszkiewicz M Analogy, similarity and factors Proceedings of the 13th International Conference on Artificial Intelligence and Law, (101-105)
- Horty J Reasons and precedent Proceedings of the 13th International Conference on Artificial Intelligence and Law, (41-50)
- Wyner A, Bench-Capon T and Atkinson K Towards formalising argumentation about legal cases Proceedings of the 13th International Conference on Artificial Intelligence and Law, (1-10)
- Wardeh M, Bench-Capon T and Coenen F (2009). PADUA, Artificial Intelligence and Law, 17:3, (183-215), Online publication date: 1-Sep-2009.
- Gordon T and Walton D Legal reasoning with argumentation schemes Proceedings of the 12th International Conference on Artificial Intelligence and Law, (137-146)
- Bench-Capon T and Modgil S Case law in extended argumentation frameworks Proceedings of the 12th International Conference on Artificial Intelligence and Law, (118-127)
- Ashley K Ontological requirements for analogical, teleological, and hypothetical legal reasoning Proceedings of the 12th International Conference on Artificial Intelligence and Law, (1-10)
- Ashley K and Brüninghaus S (2009). Automatically classifying case texts and predicting outcomes, Artificial Intelligence and Law, 17:2, (125-165), Online publication date: 1-Jun-2009.
- Wardeh M, Bench-Capon T and Coenen F Multi-party argument from experience Proceedings of the 6th international conference on Argumentation in Multi-Agent Systems, (216-235)
- Wardeh M, Bench-Capon T and Coenen F Arguments from Experience Proceedings of the 2008 conference on Computational Models of Argument: Proceedings of COMMA 2008, (405-416)
- Moens M (2007). Summarizing court decisions, Information Processing and Management: an International Journal, 43:6, (1748-1764), Online publication date: 1-Nov-2007.
- Bench-Capon T and Dunne P (2007). Argumentation in artificial intelligence, Artificial Intelligence, 171:10-15, (619-641), Online publication date: 1-Jul-2007.
- Tanaka T, Maeda N, Katagami D and Nitta K Characterized argument agent for training partner Proceedings of the 2007 conference on New frontiers in artificial intelligence, (377-389)
- Brüninghaus S and Ashley K Generating legal arguments and predictions from case texts Proceedings of the 10th international conference on Artificial intelligence and law, (65-74)
- Aleven V, Ashley K and Lynch C Helping law students to understand US Supreme Court oral arguments Proceedings of the 10th international conference on Artificial intelligence and law, (55-59)
- Chorley A and Bench-Capon T AGATHA Proceedings of the 10th international conference on Artificial intelligence and law, (45-54)
- Liu C, Chang C and Ho J Classification and clustering for case-based criminal summary judgments Proceedings of the 9th international conference on Artificial intelligence and law, (252-261)
- Bruninghaus S and Ashley K Predicting outcomes of case based legal arguments Proceedings of the 9th international conference on Artificial intelligence and law, (233-242)
- Chorley A and Bench-Capon T Developing legal knowledge based systems through theory construction Proceedings of the 9th international conference on Artificial intelligence and law, (85-86)
- Greenwood K, Capon T and McBurney P Towards a computational account of persuasion in law Proceedings of the 9th international conference on Artificial intelligence and law, (22-31)
- Brüninghaus S and Ashley K Combining case-based and model-based reasoning for predicting the outcome of legal cases Proceedings of the 5th international conference on Case-based reasoning: Research and Development, (65-79)
- Roth B A typology of moves involved in case comparison Proceedings of the 8th international conference on Artificial intelligence and law, (129-138)
- Henderson J and Bench-Capon T Dynamic arguments in a case law domain Proceedings of the 8th international conference on Artificial intelligence and law, (60-69)
- Brüninghaus S and Ashley K Improving the representation of legal case texts with information extraction methods Proceedings of the 8th international conference on Artificial intelligence and law, (42-51)
- Ashley K and McLaren B An AI investigation of citation's epistemological role Proceedings of the 8th international conference on Artificial intelligence and law, (32-41)
- Bench-Capon T and Sartor G Theory based explanation of case law domains Proceedings of the 8th international conference on Artificial intelligence and law, (12-21)
- Conrad J and Da bney D A cognitive approach to judicial opinion structure Proceedings of the 8th international conference on Artificial intelligence and law, (1-11)
- Curran K and Higgins L (2000). Web Enabled Legal Aid, Information-Knowledge-Systems Management, 2:2, (189-205), Online publication date: 1-Apr-2000.
- Bench-Capon T Some observations on modelling case based reasoning with formal argument models Proceedings of the 7th international conference on Artificial intelligence and law, (36-42)
- Brüninghaus S and Ashley K Toward adding knowledge to learning algorithms for indexing legal cases Proceedings of the 7th international conference on Artificial intelligence and law, (9-17)
Recommendations
Teaching Case-Based Argumentation Concepts Using Dialectic Arguments vs. Didactic Explanations
ITS '02: Proceedings of the 6th International Conference on Intelligent Tutoring SystemsWe compared two automated approaches to teaching distinguishing, a fundamental skill of case-based reasoning that involves assessing the relevant differences among cases in a context-sensitive way. The approaches are implemented in two versions of CATO, ...
Computing Arguments and Attacks in Assumption-Based Argumentation
CaSAPI (Credulous and Skeptical Argumentation: Prolog Implementation) 3.0 determines the acceptability of claims, using the general-purpose framework of assumption-based argumentation, under the semantics of admissible extensions. This framework reduces ...
Help design in a computer-based learning environment teaching argumentation skills through the use of double-content-examples
ICLS'08: Proceedings of the 8th international conference on International conference for the learning sciences - Volume 2Learning with self-explaining examples is an effective method in well-structured domains. We analyzed this method in teaching the complex skill of argumentation. In an experiment we compared three conditions (n = 47 students of educational sciences) ...