Unverified50% confidenceBenchmarkExact time
The study compared on four models, two in-domain corpora, and three held-out corpora, and the results show that only ASC simultaneously reduces the 'authored sentence' error rate and increases supported sentences.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedUnder the held-out evaluator, ASC's median error rate drops by 38%, the median improvement in supported sentences reaches 46%, and this holds in all test settings.69% similarUnverifiedResearch shows that in certain tasks, simply changing '请判断' to '请分析' in a prompt can cause accuracy fluctuations of 5–10 percentage points.67% similarUnverifiedAblation analysis shows that fine-tuning on the segment paradigm yields a +5.29-point improvement on the test set, while replacing the first 4,500 transcript words with 2,000 retrieved words yields only a +1.55-point improvement.65% similarUnverifiedIn a test covering 8 local models and more than 5000 calls, the wording style of the prompt (plain/normal/florid) had almost no effect on accuracy on non-math tasks, with differences of no more than 4 percentage points for models of 8B and above.65% similarUnverifiedAn insufficiently small reference corpus systematically underestimates true divergence, and the researchers introduce a source-split jackknife method that uses only reference data, which can reduce calibration error by 57% to 59%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023697API
curl https://kongchang.com/api/v1/knowledge/claims/1023697MCP
get_claim(id=1023697)