# Clarifying Semantics of In-Context Examples for Unit Test Generation

arXiv: https://arxiv.org/abs/2510.01994 · HTML: https://mlsanity.com/paper/2510.01994/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Unit Test Case Generation with Transformers and Focal Context](https://mlsanity.com/paper/2009.05617/) (2020)
- [No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation](https://mlsanity.com/paper/2305.04207/) (2023)
- [Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM](https://mlsanity.com/paper/2402.00097/) (2024)
- [Pynguin: Automated Unit Test Generation for Python](https://mlsanity.com/paper/2202.05218/) (2022)
- [HITS: High-coverage LLM-based Unit Test Generation via Method Slicing](https://mlsanity.com/paper/2408.11324/) (2024)
- [On the Evaluation of Large Language Models in Unit Test Generation](https://mlsanity.com/paper/2406.18181/) (2024)
- [A3Test: Assertion-Augmented Automated Test Case Generation](https://mlsanity.com/paper/2302.10352/) (2023)
- [Toward Understanding Deep Learning Framework Bugs](https://mlsanity.com/paper/2203.04026/) (2022)
- [CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios](https://mlsanity.com/paper/2403.19287/) (2024)
- [Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests](https://mlsanity.com/paper/2408.11710/) (2024)
- [Advancing Code Coverage: Incorporating Program Analysis with Large Language Models](https://mlsanity.com/paper/2404.04966/) (2024)
- [Evaluating Large Language Models in Detecting Test Smells](https://mlsanity.com/paper/2407.19261/) (2024)
- [CSA-Trans: Code Structure Aware Transformer for AST](https://mlsanity.com/paper/2404.05767/) (2024)
- [Test Case Purification for Improving Fault Localization](https://mlsanity.com/paper/1409.3176/) (2014)
- [Dependency-Aware Code Naturalness](https://mlsanity.com/paper/2409.00747/) (2024)
- [Reflective Unit Test Generation for Precise Type Error Detection with Large Language Models](https://mlsanity.com/paper/2507.02318/) (2025)

## Built on by (most cited first, 3 of 3)

- [Issue-Oriented Agent-Based Framework for Automated Review Comment Generation](https://mlsanity.com/paper/2511.00517/) (2025)
- [Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-Debugging](https://mlsanity.com/paper/2602.03181/) (2026)
- [Agent-Based Test Assertion Generation via Diverse Perspective Aggregation](https://mlsanity.com/paper/2608.05822/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) have enabled promising performance in unit test generation through in-context learning (ICL). However, the quality of in-context examples significantly influences the effectiveness of generated tests-poorly structured or semantically unclear test examples often lead to suboptimal outputs. In this paper, we propose CLAST, a novel technique that systematically refines unit tests to improve their semantic clarity, thereby enhancing their utility as in-context examples. The approach decomposes complex tests into logically clearer ones and improves semantic clarity through a combination of program analysis and LLM-based rewriting. We evaluated CLAST on four open-source and three industrial projects. The results demonstrate that CLAST largely outperforms UTgen, the state-of-the-art refinement technique, in both preserving test effectiveness and enhancing semantic clarity. Specifically, CLAST fully retains the original effectiveness of unit tests, while UTgen reduces compilation success rate (CSR), pass rate (PR), test coverage (Cov), and mutation score (MS) by an average of 12.90%, 35.82%, 4.65%, and 5.07%, respectively. Over 85.33% of participants in our user study preferred the semantic clarity of CLAST-refined tests. Notably, incorporating CLAST-refined tests as examples effectively improves ICL-based unit test generation approaches such as RAGGen and TELPA, resulting in an average increase of 25.97% in CSR, 28.22% in PR, and 45.99% in Cov for generated tests, compared to incorporating UTgen-refined tests. The insights from the follow-up user study not only reinforce CLAST's potential impact in software testing practice but also illuminate avenues for future research.