# Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation

arXiv: https://arxiv.org/abs/2412.15255 · HTML: https://mlsanity.com/paper/2412.15255/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 15 Dec 2024.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [Data Contamination: From Memorization to Exploitation](https://mlsanity.com/paper/2203.08242/) (2022)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Rethinking Benchmark and Contamination for Language Models with Rephrased Samples](https://mlsanity.com/paper/2311.04850/) (2023)
- [Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy](https://mlsanity.com/paper/2210.17546/) (2022)
- [Explaining Knowledge Distillation by Quantifying the Knowledge](https://mlsanity.com/paper/2003.03622/) (2020)
- [Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates](https://mlsanity.com/paper/2410.07137/) (2024)
- [TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs](https://mlsanity.com/paper/2403.00393/) (2024)
- [Sinkhorn Distance Minimization for Knowledge Distillation](https://mlsanity.com/paper/2402.17110/) (2024)

## Built on by (most cited first, 6 of 6)

- [Scaling Low-Resource MT via Synthetic Data Generation with LLMs](https://mlsanity.com/paper/2505.14423/) (2025)
- [KD4MT: A Survey of Knowledge Distillation for Machine Translation](https://mlsanity.com/paper/2602.15845/) (2026)
- [Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees](https://mlsanity.com/paper/2605.18654/) (2026)
- [Distilling Tabular Foundation Models for Structured Health Data](https://mlsanity.com/paper/2605.18702/) (2026)
- [MatheMagic: Generating Dynamic Mathematics Benchmarks Robust to Memorization](https://mlsanity.com/paper/2510.05962/) (2025)
- [LLMs in the Real World: Evaluating "AI" in Emergency Contexts](https://mlsanity.com/paper/2607.00019/) (2026)

## Abstract (arXiv)

In this paper, we show that knowledge distillation can be subverted to manipulate language model benchmark scores, revealing a critical vulnerability in current evaluation practices. We introduce "Data Laundering," a process that enables the covert transfer of benchmark-specific knowledge through seemingly legitimate intermediate training steps. Through extensive experiments with a 2-layer BERT student model, we show how this approach can achieve substantial improvements in benchmark accuracy (up to 75% on GPQA) without developing genuine reasoning capabilities. Notably, this method can be exploited intentionally or even unintentionally, as researchers may inadvertently adopt this method and inflate scores without realising the implications. While our findings demonstrate the effectiveness of this technique, we present them as a cautionary tale highlighting the urgent need for more robust evaluation methods in AI. This work aims to contribute to the ongoing discussion about evaluation integrity in AI development and the need for benchmarks that more accurately reflect true model capabilities. The code is available at https://github.com/mbzuai-nlp/datalaundering.