# Benchmarking Causal Study to Interpret Large Language Models for Source Code arXiv: https://arxiv.org/abs/2308.12415 · HTML: https://mlsanity.com/paper/2308.12415/ ## Key facts - Cited by 14 papers in the map (data through 14 Oct 2026). - Builds on 37 of its 49 references that are in the map. - First posted on arXiv 23 Aug 2023. ## Builds on (most cited first, 30 of 37) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021) - [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020) - [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023) - [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021) - [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022) - [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021) - [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019) - [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022) - [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019) - [SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair](https://mlsanity.com/paper/1901.01808/) (2018) - [Large Language Models Meet NL2Code: A Survey](https://mlsanity.com/paper/2212.09420/) (2022) - [MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation](https://mlsanity.com/paper/2208.08227/) (2022) - [The Adverse Effects of Code Duplication in Machine Learning Models of Code](https://mlsanity.com/paper/1812.06469/) (2018) - [Neural Machine Translation with Byte-Level Subwords](https://mlsanity.com/paper/1909.03341/) (2019) - [An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation](https://mlsanity.com/paper/1812.08693/) (2018) - [Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks](https://mlsanity.com/paper/2102.02017/) (2021) - [Using Pre-Trained Models to Boost Code Review Automation](https://mlsanity.com/paper/2201.06850/) (2022) - [Towards Automating Code Review Activities](https://mlsanity.com/paper/2101.02518/) (2021) - [On Learning Meaningful Code Changes via Neural Machine Translation](https://mlsanity.com/paper/1901.09102/) (2019) - [On Learning Meaningful Assert Statements for Unit Test Cases](https://mlsanity.com/paper/2002.05800/) (2020) - [A Systematic Literature Review on the Use of Deep Learning in Software Engineering Research](https://mlsanity.com/paper/2009.06520/) (2020) - [Improving ChatGPT Prompt for Code Generation](https://mlsanity.com/paper/2305.08360/) (2023) - [Sorting and Transforming Program Repair Ingredients via Deep Learning Code Similarities](https://mlsanity.com/paper/1707.04742/) (2017) - [An Empirical Study on the Usage of BERT Models for Code Completion](https://mlsanity.com/paper/2103.07115/) (2021) - [An Empirical Study on the Usage of Transformer Models for Code Completion](https://mlsanity.com/paper/2108.01585/) (2021) - [DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions](https://mlsanity.com/paper/2108.13518/) (2021) - [Using Transfer Learning for Code-Related Tasks](https://mlsanity.com/paper/2206.08574/) (2022) - [Learning How to Mutate Source Code from Bug-Fixes](https://mlsanity.com/paper/1812.10772/) (2018) ## Built on by (most cited first, 14 of 14) - [HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent](https://mlsanity.com/paper/2406.00215/) (2024) - [Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations](https://mlsanity.com/paper/2407.08983/) (2024) - [How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study](https://mlsanity.com/paper/2412.18989/) (2024) - [Neuron-Guided Interpretation of Code LLMs: Where, Why, and How?](https://mlsanity.com/paper/2512.19980/) (2025) - [Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs](https://mlsanity.com/paper/2601.14311/) (2026) - [LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review](https://mlsanity.com/paper/2604.16321/) (2026) - [A Systematic Literature Review on Explainability for Machine/Deep Learning-based Software Engineering Research](https://mlsanity.com/paper/2401.14617/) (2024) - [Knowledge-based Consistency Testing of Large Language Models](https://mlsanity.com/paper/2407.12830/) (2024) - [SnipGen: A Mining Repository Framework for Evaluating LLMs for Code](https://mlsanity.com/paper/2502.07046/) (2025) - [Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation](https://mlsanity.com/paper/2503.16771/) (2025) - [Protocode: Prototype-Driven Interpretability for Code Generation in LLMs](https://mlsanity.com/paper/2509.25247/) (2025) - [Mapping the Trust Terrain: LLMs in Software Engineering -- Insights and Perspectives](https://mlsanity.com/paper/2503.13793/) (2025) - [Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering](https://mlsanity.com/paper/2601.21070/) (2026) - [Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment](https://mlsanity.com/paper/2606.24834/) (2026) ## Abstract (arXiv) One of the most common solutions adopted by software researchers to address code generation is by training Large Language Models (LLMs) on massive amounts of source code. Although a number of studies have shown that LLMs have been effectively evaluated on popular accuracy metrics (e.g., BLEU, CodeBleu), previous research has largely overlooked the role of Causal Inference as a fundamental component of the interpretability of LLMs' performance. Existing benchmarks and datasets are meant to highlight the difference between the expected and the generated outcome, but do not take into account confounding variables (e.g., lines of code, prompt size) that equally influence the accuracy metrics. The fact remains that, when dealing with generative software tasks by LLMs, no benchmark is available to tell researchers how to quantify neither the causal effect of SE-based treatments nor the correlation of confounders to the model's performance. In an effort to bring statistical rigor to the evaluation of LLMs, this paper introduces a benchmarking strategy named Galeras comprised of curated testbeds for three SE tasks (i.e., code completion, code summarization, and commit generation) to help aid the interpretation of LLMs' performance. We illustrate the insights of our benchmarking strategy by conducting a case study on the performance of ChatGPT under distinct prompt engineering methods. The results of the case study demonstrate the positive causal influence of prompt semantics on ChatGPT's generative performance by an average treatment effect of ≈ 3%. Moreover, it was found that confounders such as prompt size are highly correlated with accuracy metrics (≈ 0.412%). The end result of our case study is to showcase causal inference evaluations, in practice, to reduce confounding bias. By reducing the bias, we offer an interpretable solution for the accuracy metric under analysis.