Unverified50% confidenceFactExact time
SWORD generates grammatically fluent but factually incorrect statements by fixing the subject and relation while replacing only the object, encompassing two types of perturbation: random entity replacement and semantically plausible attribute-based replacement
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified语义级diff能够识别函数重命名、代码重组等在文本层面显示为大量变更但语义上等价的操作，从而减少误报冲突67% similarUnverifiedFixed-character chunking strategies truncate sentences and disrupt semantic integrity, and should be replaced with intelligent semantic chunking or sliding window strategies.62% similarUnverifiedSWORD (Systematic Wikidata-based Object-Relation Distortion) is a fact-checking evaluation benchmark that generates grammatically fluent but factually incorrect statements through controlled perturbations based on Wikidata triples.61% similarUnverified每一个反复出现的标注分歧都应转化为成文规则，并配上正面示例和反面示例61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/895264API
curl https://kongchang.com/api/v1/knowledge/claims/895264MCP
get_claim(id=895264)