# Pitfalls of Evaluating Language Models with Open Benchmarks

arXiv: https://arxiv.org/abs/2507.00460 · HTML: https://mlsanity.com/paper/2507.00460/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)

## Built on by (most cited first, 7 of 7)

- [The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs](https://mlsanity.com/paper/2509.03730/) (2025)
- [Beyond "Hallucinations": A Framework for Stable Human-AI Reasoning](https://mlsanity.com/paper/2510.14665/) (2025)
- [Simulated Self-Assessment in Large Language Models: A Psychometric Approach to AI Self-Efficacy](https://mlsanity.com/paper/2511.19872/) (2025)
- [SEAR: Schema-Based Evaluation and Routing for LLM Gateways](https://mlsanity.com/paper/2603.26728/) (2026)
- [Mirror, Mirror on the Wall -- Which is the Best Model of Them All?](https://mlsanity.com/paper/2512.02043/) (2025)
- [DL3M: A Vision-to-Language Framework for Expert-Level Medical Reasoning through Deep Learning and Large Language Models](https://mlsanity.com/paper/2512.13742/) (2025)
- [DepthCharge: A Domain-Agnostic Framework for Measuring Depth-Dependent Knowledge in Large Language Models](https://mlsanity.com/paper/2603.23514/) (2026)

## Abstract (arXiv)

Open Large Language Model (LLM) benchmarks, such as HELM and BIG-Bench, provide standardized and transparent evaluation protocols that support comparative analysis, reproducibility, and systematic progress tracking in Language Model (LM) research. Yet, this openness also creates substantial risks of data leakage during LM testing--deliberate or inadvertent, thereby undermining the fairness and reliability of leaderboard rankings and leaving them vulnerable to manipulation by unscrupulous actors. We illustrate the severity of this issue by intentionally constructing cheating models: smaller variants of BART, T5, and GPT-2, fine-tuned directly on publicly available test-sets. As expected, these models excel on the target benchmarks but fail terribly to generalize to comparable unseen testing sets. We then examine task specific simple paraphrase-based safeguarding strategies to mitigate the impact of data leakage and evaluate their effectiveness and limitations. Our findings underscore three key points: (i) high leaderboard performance on limited open, static benchmarks may not reflect real-world utility; (ii) private or dynamically generated benchmarks should complement open benchmarks to maintain evaluation integrity; and (iii) a reexamination of current benchmarking practices is essential for reliable and trustworthy LM assessment.