# Incoherence as Oracle-less Measure of Error in LLM-Based Code Generation

arXiv: https://arxiv.org/abs/2507.00057 · HTML: https://mlsanity.com/paper/2507.00057/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 10 of 10)

- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Chainpoll: A high efficacy method for LLM hallucination detection](https://mlsanity.com/paper/2310.18344/) (2023)
- [QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks](https://mlsanity.com/paper/2501.17167/) (2025)
- [Enhancing LLM Code Generation with Ensembles: A Similarity-Based Selection Approach](https://mlsanity.com/paper/2503.15838/) (2025)
- [The Fault in our Stars: Quality Assessment of Code Generation Benchmarks](https://mlsanity.com/paper/2404.10155/) (2024)
- [MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking](https://mlsanity.com/paper/2501.13117/) (2025)
- [Showing LLM-Generated Code Selectively Based on Confidence of LLMs](https://mlsanity.com/paper/2410.03234/) (2024)
- [Assurances in Software Testing: A Roadmap](https://mlsanity.com/paper/1807.10255/) (2018)

## Built on by (most cited first, 6 of 6)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI](https://mlsanity.com/paper/2510.02185/) (2025)
- [N-Version Programming with Coding Agents](https://mlsanity.com/paper/2606.20158/) (2026)
- [Beyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation](https://mlsanity.com/paper/2607.24884/) (2026)
- [How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair](https://mlsanity.com/paper/2607.25873/) (2026)
- [ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation](https://mlsanity.com/paper/2608.04439/) (2026)

## Abstract (arXiv)

Generating code from a natural language programming task is one of the most successful applications of Large Language Models (LLMs). Yet, the generated program may be buggy. Without an oracle, such as an existing, correct implementation or a formal specification, can we somehow estimate how likely the generated program is correct? In this paper, we propose a measure of incorrectness, called *incoherence*, that can be estimated efficiently in the absence of an oracle and allows us to establish a lower bound on the error, i.e., the probability that the LLM-generated program for that specification is incorrect. In our experiments, our incoherence-based methodology can automatically identify about two-thirds of incorrect programs without reports of false positives for the average task. In fact, *an oracle-based evaluation of LLMs can be reliably replaced by an incoherence-based evaluation*. In particular, we find a very strong agreement between the ranking of LLMs by the number of programs deemed correct via an oracle (pass@1) and the ranking of LLMs by the number of programs deemed correct via incoherence.