TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning
This work addresses the interpretability and reliability of LLM reasoning for AI researchers and practitioners, offering a unified paradigm but is incremental in building on existing explanation methods.
The paper tackles the problem of interpreting large language model (LLM) reasoning by proposing the Trustworthy Unified Explanation Framework (TRUE), which integrates executable verification, DAG modeling, and causal analysis to provide multi-level explanations, as demonstrated through extensive experiments on reasoning benchmarks.
Large language models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, yet their decision-making processes remain difficult to interpret. Existing explanation methods often lack trustworthy structural insight and are limited to single-instance analysis, failing to reveal reasoning stability and systematic failure mechanisms. To address these limitations, we propose the Trustworthy Unified Explanation Framework (TRUE), which integrates executable reasoning verification, feasible-region directed acyclic graph (DAG) modeling, and causal failure mode analysis. At the instance level, we redefine reasoning traces as executable process specifications and introduce blind execution verification to assess operational validity. At the local structural level, we construct feasible-region DAGs via structure-consistent perturbations, enabling explicit characterization of reasoning stability and the executable region in the local input space. At the class level, we introduce a causal failure mode analysis method that identifies recurring structural failure patterns and quantifies their causal influence using Shapley values. Extensive experiments across multiple reasoning benchmarks demonstrate that the proposed framework provides multi-level, verifiable explanations, including executable reasoning structures for individual instances, feasible-region representations for neighboring inputs, and interpretable failure modes with quantified importance at the class level. These results establish a unified and principled paradigm for improving the interpretability and reliability of LLM reasoning systems.