# ConsistencyChecker: Tree-based Evaluation of LLM Generalization Capabilities

arXiv: https://arxiv.org/abs/2506.12376 · HTML: https://mlsanity.com/paper/2506.12376/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [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)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2309.11925/) (2023)
- [Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation](https://mlsanity.com/paper/2410.13640/) (2024)
- [LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks](https://mlsanity.com/paper/2502.06215/) (2025)
- [Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain](https://mlsanity.com/paper/2310.14053/) (2023)
- [Preliminary WMT24 Ranking of General MT Systems and LLMs](https://mlsanity.com/paper/2407.19884/) (2024)

## Built on by (most cited first, 5 of 5)

- [LLMs Corrupt Your Documents When You Delegate](https://mlsanity.com/paper/2604.15597/) (2026)
- [Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs](https://mlsanity.com/paper/2510.01527/) (2025)
- [Global Consistency Repair for Natural-Language Claim Sets](https://mlsanity.com/paper/2601.13600/) (2026)
- [Measuring Semantic Progress in Multi-turn Dialogue via Information Gain](https://mlsanity.com/paper/2606.12332/) (2026)
- [If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs](https://mlsanity.com/paper/2609.10123/) (2026)

## Abstract (arXiv)

Evaluating consistency in large language models (LLMs) is crucial for ensuring reliability, particularly in complex, multi-step interactions between humans and LLMs. Traditional self-consistency methods often miss subtle semantic changes in natural language and functional shifts in code or equations, which can accumulate over multiple transformations. To address this, we propose ConsistencyChecker, a tree-based evaluation framework designed to measure consistency through sequences of reversible transformations, including machine translation tasks and AI-assisted programming tasks. In our framework, nodes represent distinct text states, while edges correspond to pairs of inverse operations. Dynamic and LLM-generated benchmarks ensure a fair assessment of the model's generalization ability and eliminate benchmark leakage. Consistency is quantified based on similarity across different depths of the transformation tree. Experiments on eight models from various families and sizes show that ConsistencyChecker can distinguish the performance of different models. Notably, our consistency scores-computed entirely without using WMT paired data-correlate strongly (r > 0.7) with WMT 2024 auto-ranking, demonstrating the validity of our benchmark-free approach. Our implementation is available at: https://github.com/ulab-uiuc/consistencychecker.