Unverified50% confidenceBenchmarkExact time
Under a unified evaluation protocol, an 8.1B-parameter LLM detector's F1 score differs from LogCDM's by only 0.013-0.12.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/10/2026
First Seen
Valid until: 2/8/2027
Sources
Related Entities
Related Claims
UnverifiedOn a stratified 1,000-item test subset, the strongest LLM prompting configuration achieved an accuracy of 0.477, while the fine-tuned DistilBERT reached 0.879.68% similarUnverifiedvLLM published its DeepSeek model inference optimization results: under the corresponding test configuration, decoding throughput is within 6% of the official engine, with tests covering batch sizes from 8 to 256.66% similarUnverifiedAfter adopting a conservative fusion rule (outputting Support or Contradict only when the NLI and LLM judgments agree, and otherwise outputting Not Enough Evidence), Macro-F1 dropped to 0.7392 (Qwen3), 0.6730 (Llama 3.1) and 0.5991 (Mistral), all lower than the scores achieved when each was used alone.65% similarUnverifiedThe strongest controlled direct baseline achieved only 0.371±0.018 on the logical F1 metric, which is lower than EviDent-CBCT's 0.402.65% similarUnverifiedThe usable resolution of LLM assessment scores is about 0.5 points, not 0.1 points.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1154285API
curl https://kongchang.com/api/v1/knowledge/claims/1154285MCP
get_claim(id=1154285)