Unverified50% confidenceFactExact time
FakeSpotter provides an explanation layer that outputs results through feature-based scores, signal consistency, and a caution index.
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFakeSpotter's overall positioning is as an 'early-stage, interpretable, human-supervised' assessment tool, not intended to replace human judgment.76% similarVerifiedCommonly used evaluation benchmarks in the field of hallucination detection include TruthfulQA, HaluEval, and FActScore.72% similarUnverified该数据集的每一行都经过人工审核，核验标签准确性、理由真实与具体性、难度标签匹配度三个维度69% similarUnverifiedDetecting hallucinations requires a dedicated evaluation mechanism independent of accuracy, such as comparing model outputs with the literal correspondence to the original OCR text.69% similarUnverified低粉账号能爆说明选题本身有穿透力，是经过算法验证的纯净信号，复制借鉴价值最高69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931148API
curl https://kongchang.com/api/v1/knowledge/claims/931148MCP
get_claim(id=931148)