Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
read the original abstract
Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs' training data, it could explicitly or implicitly include test data, leading to LLMs being more susceptible to data contamination. However, due to the opacity of training data, the black-box access of models, and the rapid growth of synthetic training data, detecting and mitigating data contamination for LLMs faces significant challenges. In this paper, we propose CDD, which stands for Contamination Detection via output Distribution for LLMs. CDD necessitates only the sampled texts to detect data contamination, by identifying the peakedness of LLM's output distribution. To mitigate the impact of data contamination in evaluation, we also present TED: Trustworthy Evaluation via output Distribution, based on the correction of LLM's output distribution. To facilitate this study, we introduce two benchmarks, i.e., DetCon and ComiEval, for data contamination detection and contamination mitigation evaluation tasks. Extensive experimental results show that CDD achieves the average relative improvements of 21.8\%-30.2\% over other contamination detection approaches in terms of Accuracy, F1 Score, and AUC metrics, and can effectively detect implicit contamination. TED substantially mitigates performance improvements up to 66.9\% attributed to data contamination across various contamination setups. In real-world applications, we reveal that ChatGPT exhibits a high potential to suffer from data contamination on HumanEval benchmark.
This paper has not been read by Pith yet.
Forward citations
Cited by 11 Pith papers
-
PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data
Only two of seven LLMs produce positive returns on live Polymarket data, with MiMo-V2-Flash at 17.6% CWR and Gemini-3-Flash at 6.2% CWR while the other five lose money.
-
LiveBench: A Challenging, Contamination-Limited LLM Benchmark
LiveBench is a contamination-limited LLM benchmark with auto-scored challenging tasks from recent sources across math, coding, reasoning and more, where top models score below 70%.
-
InvestPhilBench: A Multi-Layer Dynamic Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy
InvestPhilBench is a new multi-layer benchmark for LLM procedural reasoning in investment philosophy, with BASP metrics showing composite scores saturate while gate reconstruction accuracy reveals procedural deficits.
-
Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study
Reproduction of hieroglyphic translation finds test-set contamination inflating BLEU from 37.0 to 61.5, with corrected clean baselines of 30.9-39.2.
-
PRIMETIME : Limits of LLMs in Temporal Primitives
PRIMETIME generator reveals that LLM datetime parsing and arithmetic primitives are individually unreliable but fully learnable via fine-tuning, enabling frontier-level accuracy on event planning with small LoRA models.
-
Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications
First unified survey formalizing Pretraining Data Exposure across exposure levels and reviewing attack, defense, and contamination methods for LLMs.
-
Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models
Know2Guess is a contamination-aware multi-zone benchmark for evaluating LLM knowledge boundaries with explicit abstention expectations and dual parsers.
-
Auditing Data Membership in Reinforcement Learning With Verifiable Rewards
DIBA detects membership of prompts in RLVR training by measuring reward success changes and policy behavioral drift between pre- and post-RLVR model checkpoints.
-
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
ZCP detects direct and evasive data contamination in LLMs by truncating CoT reasoning and contrasting zero-CoT accuracy on original versus perturbed isomorphic datasets, plus a Contamination Confidence metric.
-
Position: AI Evaluations Should be Grounded on a Theory of Capability
AI evaluations should be reframed as inference tasks grounded in an explicit theory of capability, with an empirical demonstration that results depend on modeling assumptions and a proposed Evaluation Card for transparency.
-
Benchmark Data Contamination of Large Language Models: A Survey
A survey reviewing benchmark data contamination in LLMs, its impact on evaluation, and alternative assessment approaches.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.