Unverified50% confidenceFactExact time
Largha-150M-v1's training mixture includes a pool of 500 error corrections, which were mined from the model's predictions on typed-decision test rows, so 0.906 is a fitting reading rather than a zero-shot result.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLargha-150M-v1 achieves a reading of 0.906 on the typed-decision English self-evaluation (400 cases / 2000 decisions), higher than the 0.735 teacher self-consistency reference, but the dataset card flags a risk of label-specific overfitting.75% similarUnverified即使只有5-10%的训练样本存在错位，也会导致VLM模型在下游任务上出现显著的性能退化71% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.69% similarUnverifiedTraditional benchmarks have become ineffective for evaluating model reasoning ability because almost every model may have seen the standard answers in its training data.69% similarUnverifiedThe 29-million-parameter encoder trained by the researchers achieved a popularity-weighted cross-fold AUC of only 0.486 on 985 statements, indistinguishable from the corpus prior.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016993API
curl https://kongchang.com/api/v1/knowledge/claims/1016993MCP
get_claim(id=1016993)