AR-LSAT: Investigating Analytical Reasoning of Text
This work addresses the problem of analytical reasoning for AI systems, but it is incremental as it builds on existing methods and highlights limitations without achieving SOTA or broad impact.
The authors tackled the challenge of analytical reasoning in text by introducing a new dataset from the Law School Admission Test (1991-2016) and found that while their Analytical Reasoning Machine (ARM) outperformed Transformer-based models, both methods significantly lagged behind human performance, with ARM achieving better results through symbolic knowledge extraction.
Analytical reasoning is an essential and challenging task that requires a system to analyze a scenario involving a set of particular circumstances and perform reasoning over it to make conclusions. In this paper, we study the challenge of analytical reasoning of text and introduce a new dataset consisting of questions from the Law School Admission Test from 1991 to 2016. We analyze what knowledge understanding and reasoning abilities are required to do well on this task. Furthermore, to address this reasoning challenge, we design two different baselines: (1) a Transformer-based method which leverages the state-of-the-art pre-trained language models and (2) Analytical Reasoning Machine (ARM), a logical-level reasoning framework extracting symbolic knowledge (e.g, participants, facts, logical functions) to deduce legitimate solutions. In our experiments, we find that the Transformer-based models struggle to solve this task as their performance is close to random guess and ARM achieves better performance by leveraging symbolic knowledge and interpretable reasoning steps. Results show that both methods still lag far behind human performance, which leave further space for future research.