ABDA-NL: A Natural-Language Scenario Explorer for Argument-Based Reasoning

2026-09-30

AI Summary

This work addresses the limitations of ASPIC-based argumentative reasoning systems, which lack natural language interaction and impede users in comprehending conclusion justifications or exploring assumptions. We introduce large language models (LLMs) into the ABDA system to construct a natural language interface. The core innovation lies in positioning the LLM as a translation bridge rather than a reasoning engine, designating the deterministic formal engine as the sole authority and requiring user verification for all model suggestions, thereby balancing interactive usability with logical rigor. By integrating grounded semantics with interactive visualization techniques, users can query conclusion statuses, explore dialectical processes, and dynamically modify rules and facts through natural language. This approach significantly lowers the barrier to entry for specialized argumentative reasoning tools.

Abstract

ABDA-NL adds a natural-language interface to ABDA, a system for argument-based discussion using ASPIC- knowledge bases under grounded semantics. Users see which conclusions are accepted, rejected, or undecided, open an interactive rendering of the grounded discussion game to learn why, explore what-if alternatives by suspending assumptions and rules or changing preferences, ask questions that are answered from a scenario's reference documents, and author new facts, assumptions, and rules in plain English. A large language model provides the bridge between language and formalism: it answers questions from the documents and the current state of the scenario, and it translates plain-English edits into candidate formal statements. The deterministic ABDA engine remains the sole source of arguments, attacks, and acceptance labels, and every proposal of the model is validated and confirmed by the user before it takes effect.

Problem

• Argument-based reasoning
• Natural language interface
• Grounded semantics
• Scenario exploration
• Large language model

Innovation

• Natural Language Interface
• Argument-Based Reasoning
• Large Language Model
• Grounded Semantics
• Human-in-the-loop Validation