# Impacts of Continued Legal Pre-Training and IFT on LLMs' Latent Representations of Human-Defined Legal Concepts

arXiv: https://arxiv.org/abs/2410.12001 · HTML: https://mlsanity.com/paper/2410.12001/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Analyzing the Structure of Attention in a Transformer Language Model](https://mlsanity.com/paper/1906.04284/) (2019)
- [Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference](https://mlsanity.com/paper/2407.11550/) (2024)
- [SaulLM-7B: A pioneering Large Language Model for Law](https://mlsanity.com/paper/2403.03883/) (2024)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks](https://mlsanity.com/paper/2311.12786/) (2023)
- [Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration](https://mlsanity.com/paper/2406.15765/) (2024)
- [Pre-trained Language Models for the Legal Domain: A Case Study on Indian Law](https://mlsanity.com/paper/2209.06049/) (2022)
- [Unveiling the Generalization Power of Fine-Tuned Large Language Models](https://mlsanity.com/paper/2403.09162/) (2024)
- [Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts](https://mlsanity.com/paper/2305.04417/) (2023)
- [Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies](https://mlsanity.com/paper/2310.18729/) (2023)
- [Harnessing GPT-3.5-turbo for Rhetorical Role Prediction in Legal Cases](https://mlsanity.com/paper/2310.17413/) (2023)
- [Extending Token Computation for LLM Reasoning](https://mlsanity.com/paper/2403.14932/) (2024)

## Abstract (arXiv)

This paper aims to offer AI & Law researchers and practitioners a more detailed understanding of whether and how continued pre-training and instruction fine-tuning (IFT) of large language models (LLMs) on legal corpora increases their utilization of human-defined legal concepts when developing global contextual representations of input sequences. We compared three models: Mistral 7B, SaulLM-7B-Base (Mistral 7B with continued pre-training on legal corpora), and SaulLM-7B-Instruct (with further IFT). This preliminary assessment examined 7 distinct text sequences from recent AI & Law literature, each containing a human-defined legal concept. We first compared the proportions of total attention the models allocated to subsets of tokens representing the legal concepts. We then visualized patterns of raw attention score alterations, evaluating whether legal training introduced novel attention patterns corresponding to structures of human legal knowledge. This inquiry revealed that (1) the impact of legal training was unevenly distributed across the various human-defined legal concepts, and (2) the contextual representations of legal knowledge learned during legal training did not coincide with structures of human-defined legal concepts. We conclude with suggestions for further investigation into the dynamics of legal LLM training.