SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have achieved strong performance on natural language to SQL (NL2SQL) benchmarks, yet their reported accuracy may be inflated by contamination from benchmark queries or structurally similar patterns seen during training. |
| Approach: | They propose a syntactic probing framework for detecting and quantifying such contamination in large language models. |
| Outcome: | The proposed framework generates syntactic variants of test queries for four widely used NL2SQL datasets. |
Similar Papers
NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for evaluating large language models using annotated benchmarks are in trouble . data contamination can cause wrong scientific conclusions being published . |
| Approach: | They argue that the evaluation of NLP tasks using annotated benchmarks is in trouble . they define different levels of data contamination and propose a community effort . |
| Outcome: | The proposed measures should detect when data from a benchmark was exposed to a model and flag papers with conclusions compromised by data contamination. |
Towards Data Contamination Detection for Modern Large Language Models: Limitations, Inconsistencies, and Oracle Challenges (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for detecting data contamination in large language models have limitations and limitations . data contamination occurs when test or evaluation data is exposed to the model during its training phases . |
| Approach: | They evaluate five different methods for detecting data contamination in large language models . they find that current methods have non-trivial limitations in their assumptions and practical applications . |
| Outcome: | The proposed methods have non-trivial limitations and difficulties in detecting contamination . the authors highlight the complexity of contamination detection in advanced LLMs . |
Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation (2025.emnlp-main)
Copied to clipboard
Simin Chen, Yiming Chen, Zexin Li, Yifan Jiang, Zhongwei Wan, Yixin He, Dezhi Ran, Tianle Gu, Haizhou Li, Tao Xie, Baishakhi Ray
| Challenge: | In the era of evaluating large language models, data contamination is an increasingly prominent concern . static benchmarking has been used for evaluation, but there are limitations of *dynamic* benchmarks . |
| Approach: | They propose a series of optimal design principles for *dynamic* benchmarking and analyze the limitations of existing *static* benchmarks. |
| Outcome: | The proposed benchmarks highlight a critical gap in the evaluation of LLMs. |
Evaluating NL2SQL via SQL2NL (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks do not address robustness to linguistic variation in NL2SQL models . |
| Approach: | They propose a schema-aligned paraphrasing framework that leverages SQL-to-NL to generate semantically equivalent, lexically diverse queries while maintaining alignment with the original schema and intent. |
| Outcome: | The proposed framework generates semantically equivalent, lexically diverse queries while maintaining alignment with the original schema and intent. |
Data Contamination Can Cross Language Barriers (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to detect contamination of public benchmarks are too superficial to reflect deeper forms of contamination. |
| Approach: | They propose generalization-based approaches to unmask a cross-lingual form of contamination that inflates LLMs’ performance while evading current detection methods. |
| Outcome: | The proposed model outperforms existing detection methods while avoiding contamination of public benchmarks in the pre-training data. |
PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models are trained on vast amounts of data, which may unintentionally or intentionally include data from commonly used benchmarks. |
| Approach: | They propose a set of requirements that practical contamination detection methods should follow to effectively detect benchmark contamination in large language models. |
| Outcome: | The proposed method detects whether the model is significantly more confident under the original benchmark. |
Investigating Data Contamination in Modern Benchmarks for Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks for large language models are inflated and inconsistent with actual performance. |
| Approach: | They propose a retrieval-based system to explore potential overlaps between benchmarks and pretraining corpora and a protocol to investigate testset slot guessing. |
| Outcome: | The proposed method exploits overlaps between evaluation benchmarks and pretraining corpora and masks a wrong answer in a multiple choice question and prompts the model to fill in the gap. |
SecureSQL: Evaluating Data Leakage of Large Language Models as Natural Language Interfaces to Databases (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on the vulnerability of large language models to SQL injection have been limited. |
| Approach: | They propose to evaluate the potential of language models to leak sensitive data when generating SQL queries. |
| Outcome: | The proposed model with the best performance has an accuracy of 61.7%, compared to humans who achieve 94% accuracy. |
Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models are contaminated with data from pretraining and finetuning tasks. |
| Approach: | They perform extensive analysis on the factors that affect model memorization and generalization, such as model size, problem difficulty, and question length. |
| Outcome: | The results show that models perform better on the subset of the benchmarks where similar solutions are seen during training. |
When Benchmarks Leak: Inference-Time Decontamination for LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | a large number of large language models (LLMs) are being evaluated for their performance, but their reliability is threatened by test set contamination. |
| Approach: | They propose a framework that decontaminates large language models by applying small perturbations to the input embedding space. |
| Outcome: | The proposed framework achieves strong decontamination effectiveness while incurring minimal degradation in benign utility. |