Unverified50% confidenceBenchmarkExact time
The research team benchmarked five current mainstream LLMs, and on factual questions, the token F1 scores were only between 0.18 and 0.30 when no source passage was provided.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/10/2026
First Seen
Valid until: 2/8/2027
Sources
Related Entities
Related Claims
UnverifiedUnder a unified evaluation protocol, an 8.1B-parameter LLM detector's F1 score differs from LogCDM's by only 0.013-0.12.71% 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 0.879.70% similarUnverifiedThe Label-Only method achieves an accuracy of 0.896 and a span F1 of 0.564, with verbatim citation improving from 0.597 before training to 0.729.70% similarUnverifiedSingle-turn tests use strict exact-parameter scoring weighted by severity (L4=8 points decreasing to L0=0 points).70% similarUnverifiedThe Macro F1 of the factor identification module is only 0.5562, significantly lower than the risk assessment and evidence tracing tasks.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1155345API
curl https://kongchang.com/api/v1/knowledge/claims/1155345MCP
get_claim(id=1155345)