# Modeling Motivated Reasoning in Law: Evaluating Strategic Role Conditioning in LLM Summarization

## TL;DR

This paper investigates how large language models tailor legal summaries based on different stakeholder roles, revealing role-consistent biases and raising concerns about motivated reasoning in legal AI applications.

## Contribution

It introduces an evaluation framework for legal summarization conditioned on stakeholder roles and demonstrates models' tendency to exhibit role-aligned selective information inclusion.

## Key findings

- Models show role-consistent selective inclusion even with balancing prompts.
- Role conditioning influences the framing and content of legal summaries.
- Findings highlight potential biases in legal LLM applications.

## Abstract

Large Language Models (LLMs) are increasingly used to generate user-tailored summaries, adapting outputs to specific stakeholders. In legal contexts, this raises important questions about motivated reasoning -- how models strategically frame information to align with a stakeholder's position within the legal system. Building on theories of legal realism and recent trends in legal practice, we investigate how LLMs respond to prompts conditioned on different legal roles (e.g., judges, prosecutors, attorneys) when summarizing judicial decisions. We introduce an evaluation framework grounded in legal fact and reasoning inclusion, also considering favorability towards stakeholders. Our results show that even when prompts include balancing instructions, models exhibit selective inclusion patterns that reflect role-consistent perspectives. These findings raise broader concerns about how similar alignment may emerge as LLMs begin to infer user roles from prior interactions or context, even without explicit role instructions. Our results underscore the need for role-aware evaluation of LLM summarization behavior in high-stakes legal settings.