Unverified50% confidenceBenchmarkExact time
When adapting the general-domain trained Whisper-small model to the Earnings22 benchmark dataset, all evaluation methods showed improvement rather than degradation on the in-domain held-out set of financial speech during the adaptation process, and the expected catastrophic forgetting did not occur.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIf the model memorized the answers to contaminated benchmarks during pre-training, information loss from compressing the context will not affect performance, rendering the reported 'lossless compression' conclusion meaningless.70% similarUnverified将全部25类数据混合从预训练BERT重新完整微调，能彻底规避灾难性遗忘，是大多数实践者推荐的首选路径70% similarVerifiedIf samples are too easy the model has nothing to learn; if they are too difficult, noisy learning signals may interfere with training; the most effective learning occurs in the region slightly above current capability but still within reach.69% similarVerifiedOverfitting refers to the phenomenon where a model performs excellently on training data but its performance drops significantly on unseen test data.69% similarUnverifiedThe expected error of a supervised learning model on unseen data can be decomposed into three components: bias², variance, and irreducible noise68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001284API
curl https://kongchang.com/api/v1/knowledge/claims/1001284MCP
get_claim(id=1001284)