<![CDATA[Background: As Indonesian court decisions become increasingly accessible through public digital repositories, artificial intelligence promises to translate dense judicial language into readable summaries, yet this promise raises a central problem: whether accessibility can be achieved without weakening legal meaning. Objective: This study evaluates how AI-generated summaries of Indonesian court decisions preserve source faithfulness, legal reasoning, and public-facing explainability. Method: Using a qualitative-dominant evaluative design, this study compares ten source-linked AI summaries with ten Indonesian court decisions through structured coding of factual alignment, legal-basis accuracy, reasoning preservation, disposition fidelity, source traceability, and public-comprehension risk. Results: The findings show that AI summaries are strongest in preserving visible textual elements, especially case identity, general legal issue, and final disposition. They are less stable when summarising legal bases, procedural thresholds, interpretive qualifications, ratio decidendi, and uncertainty. Implication: This pattern indicates that AI can support legal accessibility but may also flatten judicial reasoning into outcome-centred explanation when source constraints are not preserved. Novelty: This study contributes a multidimensional framework for evaluating legal AI summaries by linking faithfulness, reasoning fidelity, and explainability as inseparable conditions for accountable public legal communication.]]>
Copyrights © 2026
