# Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models

arXiv: https://arxiv.org/abs/2504.04372 · HTML: https://mlsanity.com/paper/2504.04372/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 81 references that are in the map.
- First posted on arXiv 6 Apr 2025.

## Builds on (most cited first, 30 of 37)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [LiveBench: A Challenging, Contamination-Limited LLM Benchmark](https://mlsanity.com/paper/2406.19314/) (2024)
- [Investigating Data Contamination in Modern Benchmarks for Large Language Models](https://mlsanity.com/paper/2311.09783/) (2023)
- [Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models](https://mlsanity.com/paper/2402.15938/) (2024)
- [DebugBench: Evaluating Debugging Capability of Large Language Models](https://mlsanity.com/paper/2401.04621/) (2024)
- [Large Language Models for Test-Free Fault Localization](https://mlsanity.com/paper/2310.01726/) (2023)
- [Bugs in Large Language Models Generated Code: An Empirical Study](https://mlsanity.com/paper/2403.08937/) (2024)
- [On the Emergence of Position Bias in Transformers](https://mlsanity.com/paper/2502.01951/) (2025)
- [A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization](https://mlsanity.com/paper/2308.05487/) (2023)
- [Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs](https://mlsanity.com/paper/2502.19411/) (2025)
- [On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations](https://mlsanity.com/paper/2008.01566/) (2020)
- [BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studies](https://mlsanity.com/paper/2401.15481/) (2024)
- [CodeMind: Evaluating Large Language Models for Code Reasoning](https://mlsanity.com/paper/2402.09664/) (2024)
- [Top Score on the Wrong Exam: On Benchmarking in Machine Learning for Vulnerability Detection](https://mlsanity.com/paper/2408.12986/) (2024)
- [Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination](https://mlsanity.com/paper/2503.04149/) (2025)
- [A Study of LLMs' Preferences for Libraries and Programming Languages](https://mlsanity.com/paper/2503.17181/) (2025)
- [Dissection of a Bug Dataset: Anatomy of 395 Patches from Defects4J](https://mlsanity.com/paper/1801.06393/) (2018)
- [Are Large Language Models Memorizing Bug Benchmarks?](https://mlsanity.com/paper/2411.13323/) (2024)

## Built on by (most cited first, 4 of 4)

- [GraphLocator: Graph-guided Causal Reasoning for Issue Localization](https://mlsanity.com/paper/2512.22469/) (2025)
- [Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets](https://mlsanity.com/paper/2505.20120/) (2025)
- [textttReMind: Understanding Deductive Code Reasoning in LLMs](https://mlsanity.com/paper/2511.00488/) (2025)
- [VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection](https://mlsanity.com/paper/2602.10787/) (2026)

## Abstract (arXiv)

Generative Large Language Models (LLMs) are increasingly used in non-generative software maintenance tasks, such as fault localization (FL). Success in FL depends on a models ability to reason about program semantics beyond surface-level syntactic and lexical features. However, widely used LLM benchmarks primarily evaluate code generation, which differs fundamentally from semantic program reasoning. Meanwhile, traditional FL benchmarks such as Defect4J and BugsInPy are either not scalable or obsolete, as their datasets have become part of LLM training data, leading to biased results. This paper presents the first large-scale empirical investigation into the robustness of LLMs fault localizability. Inspired by mutation testing, we develop an end-to-end evaluation framework that addresses key limitations in existing LLM evaluation, including data contamination, scalability, automation, and extensibility. Using real-world programs with specifications, we inject unseen faults and ask LLMs to localize them, filtering out underspecified programs where localization is ambiguous. For each successfully localized program, we apply semantic-preserving mutations (SPMs) and rerun localization to assess robustness and determine whether LLM reasoning relies on syntactic cues rather than semantics. We evaluate 10 state-of-the-art LLMs on 750,013 fault localization tasks from over 1,300 Java and Python programs. We find that SPMs cause LLMs to fail on previously localized faults in 78% of cases, and that reasoning is stronger when relevant code appears earlier in context. These results indicate that LLM code reasoning is often tied to features irrelevant to semantics. We also identify code patterns that are challenging for LLMs to reason about. Overall, our findings motivate fundamental advances in how LLMs represent, interpret, and prioritize code semantics to reason more deeply about program logic