Unverified50% confidenceBenchmarkExact time
The paper evaluates TextSeal2 on three LLMs; at a false positive rate of 10^-3 and equal output token diversity, the detection rate for 100-token answers is 8 to 22 percentage points higher than TextSeal.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedAt a 1% false positive rate, OpenAI's detector achieves a detection rate of about 80% for 200-token psychology-type texts and about 95% for 400 tokens.69% similarUnverifiedResearch from institutions including Stanford University shows that for short texts under 200 words, the false positive rate of existing detectors can be as high as tens of percentage points.68% similarUnverified有研究表明当输入文本具有明确结构化标记时,主流LLM的信息提取准确率可提升20%以上,幻觉发生率相应降低68% similarUnverifiedInter-annotator agreement among different human annotators in open-ended text quality assessment is typically only 0.6–0.8.68% similarUnverifiedIn manually proofread samples, the character error rate was only 0.68% when the text was clearly legible, but approximately 45% of sampled passages were completely uncorrectable due to source quality issues.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1115429API
curl https://kongchang.com/api/v1/knowledge/claims/1115429MCP
get_claim(id=1115429)