# Automating API Documentation with LLMs: A BERTopic Approach

arXiv: https://arxiv.org/abs/2509.05749 · HTML: https://mlsanity.com/paper/2509.05749/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 6 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Leveraging BERT for Extractive Text Summarization on Lectures](https://mlsanity.com/paper/1906.04165/) (2019)
- [Leveraging Unsupervised Learning to Summarize APIs Discussed in Stack Overflow](https://mlsanity.com/paper/2111.13962/) (2021)
- [Improving Code Example Recommendations on Informal Documentation Using BERT and Query-Aware LSH: A Comparative Study](https://mlsanity.com/paper/2305.03017/) (2023)
- [Towards Code Summarization of APIs Based on Unofficial Documentation Using NLP Techniques](https://mlsanity.com/paper/2208.06318/) (2022)

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

- [CIAO - Code In Architecture Out - Automated Software Architecture Documentation with Large Language Models](https://mlsanity.com/paper/2604.08293/) (2026)

## Abstract (arXiv)

Developers rely on API documentation, but official sources are often lengthy, complex, or incomplete. Many turn to community-driven forums like Stack Overflow for practical insights. We propose automating the summarization of informal sources, focusing on Android APIs. Using BERTopic, we extracted prevalent topics from 3.6 million Stack Overflow posts and applied extractive summarization techniques to generate concise summaries, including code snippets. A user study with 30 Android developers assessed the summaries for coherence, relevance, informativeness, and satisfaction, showing improved productivity. Integrating formal API knowledge with community-generated content enhances documentation, making API resources more accessible and actionable work.