# LLMDFA: Analyzing Dataflow in Code with Large Language Models

arXiv: https://arxiv.org/abs/2402.10754 · HTML: https://mlsanity.com/paper/2402.10754/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 56 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation](https://mlsanity.com/paper/2305.15852/) (2023)
- [Repository-Level Prompt Generation for Large Language Models of Code](https://mlsanity.com/paper/2206.12839/) (2022)
- [Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models](https://mlsanity.com/paper/2212.14834/) (2022)
- [Cumulative Reasoning with Large Language Models](https://mlsanity.com/paper/2308.04371/) (2023)
- [Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair](https://mlsanity.com/paper/2309.00608/) (2023)
- [VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection](https://mlsanity.com/paper/2205.12424/) (2022)
- [Finding Inductive Loop Invariants using Large Language Models](https://mlsanity.com/paper/2311.07948/) (2023)
- [LineVD: Statement-level Vulnerability Detection using Graph Neural Networks](https://mlsanity.com/paper/2203.05181/) (2022)
- [Ranking LLM-Generated Loop Invariants for Program Verification](https://mlsanity.com/paper/2310.09342/) (2023)
- [Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection](https://mlsanity.com/paper/2212.08108/) (2022)
- [The Hitchhiker's Guide to Program Analysis: A Journey with Large Language Models](https://mlsanity.com/paper/2308.00245/) (2023)
- [Optimal Neural Program Synthesis from Multimodal Specifications](https://mlsanity.com/paper/2010.01678/) (2020)
- [Can ChatGPT support software verification?](https://mlsanity.com/paper/2311.02433/) (2023)
- [Beware of the Unexpected: Bimodal Taint Analysis](https://mlsanity.com/paper/2301.10545/) (2023)
- [Enhancing Robot Program Synthesis Through Environmental Context](https://mlsanity.com/paper/2312.08250/) (2023)
- [Principles and Practices of Large-Scale Code Analysis at Ant Group: A Data- and Logic-Oriented Approach](https://mlsanity.com/paper/2401.01571/) (2024)

## Built on by (most cited first, 22 of 22)

- [RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing](https://mlsanity.com/paper/2501.18160/) (2025)
- [ProSec: Fortifying Code LLMs with Proactive Security Alignment](https://mlsanity.com/paper/2411.12882/) (2024)
- [The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap](https://mlsanity.com/paper/2412.06512/) (2024)
- [Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineering](https://mlsanity.com/paper/2504.07137/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Locus: Agentic Predicate Synthesis for Directed Fuzzing](https://mlsanity.com/paper/2508.21302/) (2025)
- [RFCAudit: An LLM Agent for Functional Bug Detection in Network Protocols](https://mlsanity.com/paper/2506.00714/) (2025)
- [Large Language Models for Validating Network Protocol Parsers](https://mlsanity.com/paper/2504.13515/) (2025)
- [Trace Gadgets: Minimizing Code Context for Machine Learning-Based Vulnerability Prediction](https://mlsanity.com/paper/2504.13676/) (2025)
- [Reducing False Positives in Static Bug Detection with LLMs: An Empirical Study in Industry](https://mlsanity.com/paper/2601.18844/) (2026)
- [The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs](https://mlsanity.com/paper/2504.11711/) (2025)
- [Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing](https://mlsanity.com/paper/2509.14335/) (2025)
- [Generative transformations and patterns in LLM-native approaches for software verification and falsification](https://mlsanity.com/paper/2404.09384/) (2024)
- [CRABS: A syntactic-semantic pincer strategy for bounding LLM interpretation of Python notebooks](https://mlsanity.com/paper/2507.11742/) (2025)
- [An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning](https://mlsanity.com/paper/2605.11006/) (2026)
- [Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents](https://mlsanity.com/paper/2605.29910/) (2026)
- [Transferable Self-Evolving Playbooks for Agentic Security Auditing](https://mlsanity.com/paper/2606.16420/) (2026)
- [Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection](https://mlsanity.com/paper/2606.30587/) (2026)
- [FlowArk: Boosting Agentic Data-flow Analysis for Android Apps via Context-Aware Knowledge Reuse](https://mlsanity.com/paper/2607.11308/) (2026)
- [ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments](https://mlsanity.com/paper/2607.24964/) (2026)
- [On Predicting Vulnerability Severity Using In-Context Learning: An Industrial Case Study](https://mlsanity.com/paper/2608.22089/) (2026)
- [WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses](https://mlsanity.com/paper/2609.36635/) (2026)

## Abstract (arXiv)

Dataflow analysis is a fundamental code analysis technique that identifies dependencies between program values. Traditional approaches typically necessitate successful compilation and expert customization, hindering their applicability and usability for analyzing uncompilable programs with evolving analysis needs in real-world scenarios. This paper presents LLMDFA, an LLM-powered compilation-free and customizable dataflow analysis framework. To address hallucinations for reliable results, we decompose the problem into several subtasks and introduce a series of novel strategies. Specifically, we leverage LLMs to synthesize code that outsources delicate reasoning to external expert tools, such as using a parsing library to extract program values of interest and invoking an automated theorem prover to validate path feasibility. Additionally, we adopt a few-shot chain-of-thought prompting to summarize dataflow facts in individual functions, aligning the LLMs with the program semantics of small code snippets to mitigate hallucinations. We evaluate LLMDFA on synthetic programs to detect three representative types of bugs and on real-world Android applications for customized bug detection. On average, LLMDFA achieves 87.10% precision and 80.77% recall, surpassing existing techniques with F1 score improvements of up to 0.35. We have open-sourced LLMDFA at https://github.com/chengpeng-wang/LLMDFA.