Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation

• URL: http://arxiv.org/abs/2406.13990v2
• Date: Sun, 23 Jun 2024 16:46:00 GMT
• Title: Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation
• Authors: Qin Zhu, Qingyuan Cheng, Runyu Peng, Xiaonan Li, Tengxiao Liu, Ru Peng, Xipeng Qiu, Xuanjing Huang,
• Abstract summary: Leakage of benchmarks can prevent the accurate assessment of large language models' true performance. We propose Inference-Time Decontamination (ITD) to address this issue. ITD reduces inflated accuracy by 22.9% on GSM8K and 19.0% on MMLU.
• Score: 61.350306618479365
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The training process of large language models (LLMs) often involves varying degrees of test data contamination. Although current LLMs are achieving increasingly better performance on various benchmarks, their performance in practical applications does not always match their benchmark results. Leakage of benchmarks can prevent the accurate assessment of LLMs' true performance. However, constructing new benchmarks is costly, labor-intensive and still carries the risk of leakage. Therefore, in this paper, we ask the question, Can we reuse these leaked benchmarks for LLM evaluation? We propose Inference-Time Decontamination (ITD) to address this issue by detecting and rewriting leaked samples without altering their difficulties. ITD can mitigate performance inflation caused by memorizing leaked benchmarks. Our proof-of-concept experiments demonstrate that ITD reduces inflated accuracy by 22.9% on GSM8K and 19.0% on MMLU. On MMLU, using Inference-time Decontamination can lead to a decrease in the results of Phi3 and Mistral by 6.7% and 3.6% respectively. We hope that ITD can provide more truthful evaluation results for large language models.

Related papers

• LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks [15.584759853972992]
  Large Language Models (LLMs) are widely utilized in software engineering (SE) tasks, such as code generation and automated program repair. Their reliance on extensive and often undisclosed pre-training datasets raises significant concerns about data leakage. This paper presents the first large-scale analysis of data leakage in 83 SE benchmarks concerning LLMs.
  arXiv  Detail & Related papers  (2025-02-10T07:33:49Z)
• MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark [57.999567012489706]
  We propose a contamination-free and more challenging benchmark called MMLU-CF. This benchmark reassesses LLMs' understanding of world knowledge by averting both unintentional and malicious data leakage. Our evaluation of mainstream LLMs reveals that the powerful GPT-4o achieves merely a 5-shot score of 73.4% and a 0-shot score of 71.9% on the test set.
  arXiv  Detail & Related papers  (2024-12-19T18:58:04Z)
• AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge [68.39683427262335]
  Existing studies fail to guarantee contamination-free evaluation as newly collected data may contain pre-existing knowledge. We propose AntiLeak-Bench, an automated anti-leakage benchmarking framework.
  arXiv  Detail & Related papers  (2024-12-18T09:53:12Z)
• PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models [41.772263447213234]
  Large language models (LLMs) are known to be trained on vast amounts of data, which may unintentionally or intentionally include data from commonly used benchmarks. This inclusion can lead to cheatingly high scores on model leaderboards, yet result in disappointing performance in real-world applications. We introduce PaCoST, a Paired Confidence Significance Testing to effectively detect benchmark contamination in LLMs.
  arXiv  Detail & Related papers  (2024-06-26T13:12:40Z)
• MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures [57.886592207948844]
  We propose MixEval, a new paradigm for establishing efficient, gold-standard evaluation by strategically mixing off-the-shelf benchmarks. It bridges (1) comprehensive and well-distributed real-world user queries and (2) efficient and fairly-graded ground-truth-based benchmarks, by matching queries mined from the web with similar queries from existing benchmarks.
  arXiv  Detail & Related papers  (2024-06-03T05:47:05Z)
• Rethinking Benchmark and Contamination for Language Models with Rephrased Samples [49.18977581962162]
  Large language models are increasingly trained on all the data ever produced by humans. Many have raised concerns about the trustworthiness of public benchmarks due to potential contamination in pre-training or fine-tuning datasets.
  arXiv  Detail & Related papers  (2023-11-08T17:35:20Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.