# Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification

arXiv: https://arxiv.org/abs/2606.20929 · HTML: https://mlsanity.com/paper/2606.20929/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Neural Legal Judgment Prediction in English](https://mlsanity.com/paper/1906.02059/) (2019)
- [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](https://mlsanity.com/paper/1807.02478/) (2018)
- [LLM Internal States Reveal Hallucination Risk Faced With a Query](https://mlsanity.com/paper/2407.03282/) (2024)
- [ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation](https://mlsanity.com/paper/2105.13562/) (2021)
- [Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark](https://mlsanity.com/paper/2110.00806/) (2021)
- [On Early Detection of Hallucinations in Factual Question Answering](https://mlsanity.com/paper/2312.14183/) (2023)
- [Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction](https://mlsanity.com/paper/2307.08321/) (2023)
- [Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning](https://mlsanity.com/paper/2510.02091/) (2025)
- [Do LLM hallucination detectors suffer from low-resource effect?](https://mlsanity.com/paper/2601.16766/) (2026)
- [Advantages of Domain Knowledge Injection for Legal Document Summarization: A Case Study on Summarizing Indian Court Judgments in English and Hindi](https://mlsanity.com/paper/2602.07382/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly being adopted in the legal domain. However, despite their strong performance, LLMs are prone to generating incorrect or hallucinated outputs, raising serious concerns about their reliability in high-stakes domains such as law. Detecting the correctness of responses of LLM-based systems is therefore a critical challenge. In this work, we explore the potential of leveraging internal artifacts of LLM to detect the correctness of their predictions in legal-domain classification tasks. We develop approaches that utilize features derived from these internal artifacts to build downstream classifiers capable of identifying incorrect LLM outputs. We evaluate our approach on two representative legal classification tasks: bail decision prediction and statute violation prediction. Our experimental results demonstrate that LLMs' internal artifacts are reliable indicators for detecting incorrect predictions in legal classification tasks, and can be applied to enhance the reliability of LLM-based classification systems.