Unverified50% confidenceFactExact time
The research team generated 470,400 responses on three datasets—FEVER, FEVEROUS, and SciFact—using two 8B-scale large language models (Qwen and Llama).
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe study sampled 1,242 English-only prompts from six data sources: Dolly-15k, LMSYS-Chat-1M, WildChat-1M, MMLU, GSM8K, and HellaSwag61% similarUnverifiedThe research team released a multi-perspective dataset called NormReact, containing 450 norm violation scenarios.59% similarUnverifiedThe Q2D-Web dataset covers ten languages and dozens of domains.57% similarUnverifiedThe dataset comes from the team's open-source NAP (Neutrae Agent Platform) project; 72 valid logs were filtered from 2,893 raw sessions, ultimately constructing 38 fine-grained scenario matrices.57% similarVerifiedVector databases such as FAISS, Chroma, and Weaviate build indexes by encoding text as high-dimensional vectors, enabling semantic similarity retrieval in milliseconds.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946280API
curl https://kongchang.com/api/v1/knowledge/claims/946280MCP
get_claim(id=946280)