Reasoning is about giving reasons
Krunal Shah, Dan Roth

TL;DR
This paper introduces the Representation of the Logical Structure (RLS), an intermediate form capturing the logical atoms and rules of natural language arguments, enabling more interpretable and versatile reasoning in AI systems.
Contribution
It proposes the RLS framework to explicitly model the logical structure of arguments, improving reasoning interpretability and extending reasoning capabilities beyond rule chaining.
Findings
High accuracy in extracting logical structures from natural language arguments
Supports diverse reasoning tasks including abduction and contradiction detection
Enhances explanation generation in reasoning datasets
Abstract
Convincing someone of the truth value of a premise requires understanding and articulating the core logical structure of the argument which proves or disproves the premise. Understanding the logical structure of an argument refers to understanding the underlying "reasons" which make up the proof or disproof of the premise - as a function of the "logical atoms" in the argument. While it has been shown that transformers can "chain" rules to derive simple arguments, the challenge of articulating the "reasons" remains. Not only do current approaches to chaining rules suffer in terms of their interpretability, they are also quite constrained in their ability to accommodate extensions to theoretically equivalent reasoning tasks - a model trained to chain rules cannot support abduction or identify contradictions. In this work we suggest addressing these shortcomings by identifying an…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Explainable Artificial Intelligence (XAI) · Multimodal Machine Learning Applications
