OpenExempt: A Diagnostic Benchmark for Legal Reasoning and a Framework for Creating Custom Benchmarks on Demand
This provides a diagnostic tool for researchers and practitioners to better understand and improve reasoning in language models, specifically in the legal domain, though it is incremental as it builds on existing benchmarking approaches.
The authors tackled the challenge of evaluating language models in complex legal reasoning by introducing OpenExempt, a framework that dynamically generates diagnostic tasks from U.S. Bankruptcy Code statutes, resulting in a benchmark with 9,765 samples that revealed sharp performance cliffs in 13 models under longer reasoning paths and obfuscating statements.
Reasoning benchmarks have played a crucial role in the progress of language models. Yet rigorous evaluation remains a significant challenge as static question-answer pairs provide only a snapshot of performance, compressing complex behavior into a single accuracy metric. This limitation is especially true in complex, rule-bound domains such as law, where existing benchmarks are costly to build and ill suited for isolating specific failure modes. To address this, we introduce OpenExempt, a framework and benchmark for diagnostic evaluation of legal reasoning. The OpenExempt Framework uses expert-crafted symbolic representations of U.S. Bankruptcy Code statutes to dynamically generate a large space of natural language reasoning tasks and their machine-computable solutions on demand. This gives users fine-grained control over task complexity and scope, allowing individual reasoning skills to be probed in isolation. Using this system, we construct the OpenExempt Benchmark, a diagnostic benchmark for legal reasoning with 9,765 samples across nine evaluation suites designed to carefully probe model capabilities. Experiments on 13 diverse language models reveal sharp performance cliffs that emerge only under longer reasoning paths and in the presence of obfuscating statements. We release the framework and benchmark publicly to support research aimed at understanding and improving the next generation of reasoning systems.