# Multiclass Classification of Policy Documents with Large Language Models

arXiv: https://arxiv.org/abs/2310.08167 · HTML: https://mlsanity.com/paper/2310.08167/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 12 Oct 2023.

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning](https://mlsanity.com/paper/2304.06588/) (2023)
- [Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks](https://mlsanity.com/paper/2304.10145/) (2023)
- [Large Language Models Can Be Used to Estimate the Latent Positions of Politicians](https://mlsanity.com/paper/2303.12057/) (2023)
- [News Verifiers Showdown: A Comparative Performance Evaluation of ChatGPT 3.5, ChatGPT 4.0, Bing AI, and Bard in News Fact-Checking](https://mlsanity.com/paper/2306.17176/) (2023)
- [Keyword Assisted Topic Models](https://mlsanity.com/paper/2004.05964/) (2020)

## Built on by (most cited first, 1 of 1)

- [Customized Generative AI Agent for Transportation Engineering Practice: A Development and Continued Pre-training Guideline](https://mlsanity.com/paper/2606.29014/) (2026)

## Abstract (arXiv)

Classifying policy documents into policy issue topics has been a long-time effort in political science and communication disciplines. Efforts to automate text classification processes for social science research purposes have so far achieved remarkable results, but there is still a large room for progress. In this work, we test the prediction performance of an alternative strategy, which requires human involvement much less than full manual coding. We use the GPT 3.5 and GPT 4 models of the OpenAI, which are pre-trained instruction-tuned Large Language Models (LLM), to classify congressional bills and congressional hearings into Comparative Agendas Project's 21 major policy issue topics. We propose three use-case scenarios and estimate overall accuracies ranging from %58-83 depending on scenario and GPT model employed. The three scenarios aims at minimal, moderate, and major human interference, respectively. Overall, our results point towards the insufficiency of complete reliance on GPT with minimal human intervention, an increasing accuracy along with the human effort exerted, and a surprisingly high accuracy achieved in the most humanly demanding use-case. However, the superior use-case achieved the %83 accuracy on the %65 of the data in which the two models agreed, suggesting that a similar approach to ours can be relatively easily implemented and allow for mostly automated coding of a majority of a given dataset. This could free up resources allowing manual human coding of the remaining %35 of the data to achieve an overall higher level of accuracy while reducing costs significantly.