Unverified50% confidenceBenchmarkExact time
The experiments use LLaDA-8B-Base on five reasoning benchmarks, and DiVR raises the average accuracy of the fine-tuned generator from 35.3% to 43.4%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/13/2026
First Seen
Valid until: 2/11/2027
Sources
Related Entities
Related Claims
UnverifiedCompared with a strong adaptive allocation baseline, this method achieved absolute accuracy improvements of up to 3.73 percentage points (LLaDA) and 7.33 percentage points (Dream) on MATH-500.73% similarUnverifiedThe fine-tuned Qwen3.5-4B model improved accuracy on BU Bench V1 from 15% to 53%.72% similarUnverifiedOn a stratified 1,000-item test subset, the strongest LLM prompting configuration achieved an accuracy of 0.477, while the fine-tuned DistilBERT reached 0.879.72% similarUnverifiedIn the LongMemEval benchmark, BM25 accuracy improved from 78.8% to 85.2% with 5 chunks.71% similarUnverifiedThe locally run Gemma 26B achieved an accuracy of only 49.2% across 453 scored predictions, while its paired always-predict-up baseline had an accuracy of 53.4%.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1166057API
curl https://kongchang.com/api/v1/knowledge/claims/1166057MCP
get_claim(id=1166057)