# Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain

arXiv: https://arxiv.org/abs/2310.14053 · HTML: https://mlsanity.com/paper/2310.14053/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 21 Oct 2023.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [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)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [The Stack: 3 TB of permissively licensed source code](https://mlsanity.com/paper/2211.15533/) (2022)
- [Large Language Models for Code: Security Hardening and Adversarial Testing](https://mlsanity.com/paper/2302.05319/) (2023)
- [Synthetic QA Corpora Generation with Roundtrip Consistency](https://mlsanity.com/paper/1906.05416/) (2019)
- [Mapping Language to Code in Programmatic Context](https://mlsanity.com/paper/1808.09588/) (2018)
- [CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code](https://mlsanity.com/paper/2302.05527/) (2023)
- [Logic-Guided Data Augmentation and Regularization for Consistent Question Answering](https://mlsanity.com/paper/2004.10157/) (2020)
- [A Logic-Driven Framework for Consistency of Neural Models](https://mlsanity.com/paper/1909.00126/) (2019)
- [Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge](https://mlsanity.com/paper/1808.08609/) (2018)
- [TRACED: Execution-aware Pre-training for Source Code](https://mlsanity.com/paper/2306.07487/) (2023)
- [Towards Learning (Dis)-Similarity of Source Code from Program Contrasts](https://mlsanity.com/paper/2110.03868/) (2021)
- [Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses](https://mlsanity.com/paper/2305.11662/) (2023)

## Built on by (most cited first, 30 of 31)

- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [CodeMind: Evaluating Large Language Models for Code Reasoning](https://mlsanity.com/paper/2402.09664/) (2024)
- [HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent](https://mlsanity.com/paper/2406.00215/) (2024)
- [Measuring General Intelligence with Generated Games](https://mlsanity.com/paper/2505.07215/) (2025)
- [Unsupervised Evaluation of Code LLMs with Round-Trip Correctness](https://mlsanity.com/paper/2402.08699/) (2024)
- [The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?](https://mlsanity.com/paper/2402.19475/) (2024)
- [ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.15543/) (2025)
- [Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code](https://mlsanity.com/paper/2312.14856/) (2023)
- [SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations](https://mlsanity.com/paper/2510.04398/) (2025)
- [LLMs Corrupt Your Documents When You Delegate](https://mlsanity.com/paper/2604.15597/) (2026)
- [A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models](https://mlsanity.com/paper/2501.18482/) (2025)
- [Leveraging Large Language Models to Develop Heuristics for Emerging Optimization Problems](https://mlsanity.com/paper/2503.03350/) (2025)
- [Chain-of-Descriptions: Improving Code LLMs for VHDL Code Generation and Summarization](https://mlsanity.com/paper/2507.12308/) (2025)
- [tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)](https://mlsanity.com/paper/2402.02456/) (2024)
- [ConsistencyChecker: Tree-based Evaluation of LLM Generalization Capabilities](https://mlsanity.com/paper/2506.12376/) (2025)
- [Assessing Coherency and Consistency of Code Execution Reasoning by Large Language Models](https://mlsanity.com/paper/2510.15079/) (2025)
- [Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility](https://mlsanity.com/paper/2601.13398/) (2026)
- [Preventing Rogue Agents Improves Multi-Agent Collaboration](https://mlsanity.com/paper/2502.05986/) (2025)
- [Integrating Expert Knowledge into Logical Programs via LLMs](https://mlsanity.com/paper/2502.12275/) (2025)
- [SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.27786/) (2026)
- [CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models](https://mlsanity.com/paper/2503.23231/) (2025)
- [Probing the Lack of Stable Internal Beliefs in LLMs](https://mlsanity.com/paper/2603.25187/) (2026)
- [Knowledge-based Consistency Testing of Large Language Models](https://mlsanity.com/paper/2407.12830/) (2024)
- [Can Large Language Models Understand Intermediate Representations in Compilers?](https://mlsanity.com/paper/2502.06854/) (2025)
- [EVALOOOP: A Self-Consistency-Centered Framework for Assessing Large Language Model Robustness in Programming](https://mlsanity.com/paper/2505.12185/) (2025)
- [Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMs](https://mlsanity.com/paper/2511.02197/) (2025)
- [Algorithmic Prompt-Augmentation for Efficient LLM-Based Heuristic Design for A* Search](https://mlsanity.com/paper/2601.19622/) (2026)
- [Boosting Self-Consistency with Ranking](https://mlsanity.com/paper/2606.05054/) (2026)
- [LeCov: Multi-level Testing Criteria for Large Language Models](https://mlsanity.com/paper/2408.10474/) (2024)
- [Learning by Teaching: Engaging Students as Instructors of Large Language Models in Computer Science Education](https://mlsanity.com/paper/2508.05979/) (2025)

## Abstract (arXiv)

Code Large Language Models (Code LLMs) are being increasingly employed in real-life applications, so evaluating them is critical. While the conventional accuracy evaluates the performance of Code LLMs on a set of individual tasks, their self-consistency across different tasks is overlooked. Intuitively, a trustworthy model should be self-consistent when generating natural language specifications for its own code and generating code for its own specifications. Failure to preserve self-consistency reveals a lack of understanding of the shared semantics underlying natural language and programming language, and therefore undermines the trustworthiness of a model. In this paper, we first formally define the self-consistency of Code LLMs and then design a framework, IdentityChain, which effectively and efficiently evaluates the self-consistency and conventional accuracy of a model at the same time. We study eleven Code LLMs and show that they fail to preserve self-consistency, which is indeed a distinct aspect from conventional accuracy. Furthermore, we show that IdentityChain can be used as a model debugging tool to expose weaknesses of Code LLMs by demonstrating three major weaknesses that we identify in current models using IdentityChain. Our code is available at https://github.com/marcusm117/IdentityChain.