← Back to all news
arXiv Computation and Language By Xingyao Xiao (Stanford University), Yihong Cheng (City University of Macau)

Contamination Inflates Scores but Rarely Reorders Large Language Model Leaderboards

Read the original on arXiv Computation and Language →

The paper investigates how benchmark contamination—leakage of test items into training data—affects large language model (LLM) leaderboards. By comparing original test items with semantically equivalent paraphrases, the authors measure contamination as a violation of anchor-item invariance and find that it inflates absolute scores but rarely changes model rankings. Across 47 public models and 74 finetuned models on four benchmarks, the rank correlation between standard and paraphrase-controlled leaderboards is 0.997, with only a handful of cases showing differential contamination that could alter rankings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Jun 3

CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks

arXiv:2606. 03650v1 Announce Type: cross Abstract: Choosing or ranking language models for a specific application is hardest when no task-specific labeled data exists, and standard public benchmarks cannot be trusted, their items having likely leaked into pretraining, so scores reflect memorization rather than fitness.

By Alexander Apartsin, Yehudit Aperstein
llmsbenchmarkssafety
More like this →
arXiv AI
Sep 1

Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation

The paper introduces a new taxonomy for benchmark contamination that categorizes leakage by the mitigation it defeats—direct, derivative, temporal, distributional, and acquired—covering both training‑time and evaluation‑time scenarios. It proposes a four‑field disclosure protocol to record contamination status alongside benchmark scores, and provides a JSON schema, validator, and examples. An empirical study of 41 documents using a pre‑registered instrument shows limited reporting of contamination types and variable reliability, highlighting gaps in current disclosure practices.

By Johanna Angulo, V\'ictor Yeste, Hector Espinos-Morato
benchmarks
More like this →
arXiv AI
Oct 9

Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora

The study investigates how exposing large language models to Arabic translations of English benchmark tasks can hide data contamination from standard English-only detection methods. By testing four instruction-tuned models with increasing Arabic exposure, the authors find that traditional probes like TS-Guessing and Min-K%++ fail to detect contamination, yet English performance still improves. They propose a new Translation-Aware Contamination Detection (TACD) method that uses cross-lingual consistency and choice reordering to reveal contamination effects that are otherwise invisible to English-only diagnostics.

By Chaymaa Abbas, Nour Shammaa, Mariette Awad
llmsbenchmarks
More like this →