# Modeling Legal Reasoning: LM Annotation at the Edge of Human Agreement

arXiv: https://arxiv.org/abs/2310.18440 · HTML: https://mlsanity.com/paper/2310.18440/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 27 Oct 2023.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators](https://mlsanity.com/paper/2303.16854/) (2023)
- [LEGAL-BERT: The Muppets straight out of Law School](https://mlsanity.com/paper/2010.02559/) (2020)
- [ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning](https://mlsanity.com/paper/2304.06588/) (2023)
- [Stance Detection: A Practical Guide to Classifying Political Beliefs in Text](https://mlsanity.com/paper/2305.01723/) (2023)

## Built on by (most cited first, 17 of 17)

- [LEXam: Benchmarking Legal Reasoning on 340 Law Exams](https://mlsanity.com/paper/2505.12864/) (2025)
- [Codebook LLMs: Evaluating LLMs as Measurement Tools for Political Science Concepts](https://mlsanity.com/paper/2407.10747/) (2024)
- [Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval](https://mlsanity.com/paper/2403.18405/) (2024)
- [Evaluation is all you need. Prompting Generative Large Language Models for Annotation Tasks in the Social Sciences. A Primer using Open Models](https://mlsanity.com/paper/2401.00284/) (2023)
- [Evaluating AI for Law: Bridging the Gap with Open-Source Solutions](https://mlsanity.com/paper/2404.12349/) (2024)
- [Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings](https://mlsanity.com/paper/2405.16820/) (2024)
- [Automate or Assist? The Role of Computational Models in Identifying Gendered Discourse in US Capital Trial Transcripts](https://mlsanity.com/paper/2407.12500/) (2024)
- [The Implications of Open Generative Models in Human-Centered Data Science Work: A Case Study with Fact-Checking Organizations](https://mlsanity.com/paper/2408.01962/) (2024)
- [Tasks and Roles in Legal AI: Data Curation, Annotation, and Verification](https://mlsanity.com/paper/2504.01349/) (2025)
- [Hatred Stems from Ignorance! Distillation of the Persuasion Modes in Countering Conversational Hate Speech](https://mlsanity.com/paper/2403.15449/) (2024)
- [Says Who? Effective Zero-Shot Annotation of Focalization](https://mlsanity.com/paper/2409.11390/) (2024)
- [What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification](https://mlsanity.com/paper/2510.03541/) (2025)
- [Misinformation with Legal Consequences (MisLC): A New Task Towards Harnessing Societal Harm of Misinformation](https://mlsanity.com/paper/2410.03829/) (2024)
- [Op-Fed: Opinion, Stance, and Monetary Policy Annotations on FOMC Transcripts Using Active Learning](https://mlsanity.com/paper/2509.13539/) (2025)
- [Mining Legal Arguments to Study Judicial Formalism](https://mlsanity.com/paper/2512.11374/) (2025)
- [AI-Assisted Moot Courts: Simulating Justice-Specific Questioning in Oral Arguments](https://mlsanity.com/paper/2603.04718/) (2026)
- [CFMatch: Aligning Automated Answer Equivalence Evaluation with Expert Judgments For Open-Domain Question Answering](https://mlsanity.com/paper/2401.13170/) (2024)

## Abstract (arXiv)

Generative language models (LMs) are increasingly used for document class-prediction tasks and promise enormous improvements in cost and efficiency. Existing research often examines simple classification tasks, but the capability of LMs to classify on complex or specialized tasks is less well understood. We consider a highly complex task that is challenging even for humans: the classification of legal reasoning according to jurisprudential philosophy. Using a novel dataset of historical United States Supreme Court opinions annotated by a team of domain experts, we systematically test the performance of a variety of LMs. We find that generative models perform poorly when given instructions (i.e. prompts) equal to the instructions presented to human annotators through our codebook. Our strongest results derive from fine-tuning models on the annotated dataset; the best performing model is an in-domain model, LEGAL-BERT. We apply predictions from this fine-tuned model to study historical trends in jurisprudence, an exercise that both aligns with prominent qualitative historical accounts and points to areas of possible refinement in those accounts. Our findings generally sound a note of caution in the use of generative LMs on complex tasks without fine-tuning and point to the continued relevance of human annotation-intensive classification methods.