Unverified50% confidenceBenchmarkExact time
On the cluster panel, replacing the model's structured decision-making with code (based on the same extracted facts) improved family accuracy by an average of 20.5 percentage points, with Llama 3.1 8B rising from 1% under self-judgment to 56% under code adjudication.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe text-only baseline model achieved a decision accuracy of 33.33%, which improved to 93.33% after introducing dual evidence tokens.70% similarUnverifiedFairness instructions had limited effect: family accuracy changed by only −0.3 percentage points on the cluster six-model panel and +2.5 percentage points on Kaggle, with confidence intervals spanning zero in both cases.69% similarUnverifiedThe gap between selection and generation exceeds 50 percentage points, revealing that reliability is far lower than benchmarks suggest when users need the model to directly write out kinship terms.68% similarUnverifiedUnder the influence of multi-turn narratives, the models' final judgments shifted by an average of 25 percentage points compared to matched single-turn baselines.66% similarUnverifiedIn code repair tasks, the success rate using a static validator was 26.3%, rising to 29.2% after introducing predictive selection, and reaching 31.2% after world model adaptation65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003877API
curl https://kongchang.com/api/v1/knowledge/claims/1003877MCP
get_claim(id=1003877)