Unverified50% confidenceFactExact time
Benchmark contamination refers to the situation where benchmark questions have entered a model's training data, causing the model to "recall answers" rather than genuinely reason, inflating benchmark scores and failing to reflect actual capability.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
Unverified蒸馏训练范式导致开源模型学习到经过高度过滤、几乎不包含失败和纠错过程的数据分布，使模型形成不愿自我纠正的性格79% similarUnverifiedData contamination refers to test problems having already appeared in pretraining corpora, causing a model's high scores to more closely reflect memorization rather than reasoning.78% similarUnverifiedAutoregressive models suffer from the exposure bias problem, whereby the model sees real prefixes during training but faces self-generated erroneous prefixes during inference, causing errors to accumulate progressively.78% similarUnverifiedThe data contamination problem refers to the possibility that a model may have already encountered ideas or partial proofs during training that researchers have not yet formally published.78% similarUnverifiedOn contaminated benchmarks, models can directly extract answers from parametric memory rather than relying on in-context retrieval, rendering the reported lossless-compression conclusions meaningless.78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/966919API
curl https://kongchang.com/api/v1/knowledge/claims/966919MCP
get_claim(id=966919)