Unverified50% confidenceFactExact time
Evaluation uses automatic metrics (ROUGE and BLEU) and answer accuracy on multiple-choice generation, supplemented by a five-criteria human evaluation protocol.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe evaluation adopted two approaches: automatic scoring based on large language models (LLMs) and human evaluation by 11 annotators.77% similarVerifiedMainstream approaches to agent evaluation include LLM-as-Judge, trajectory matching, and outcome verification.75% similarUnverifiedCurrent mainstream LLM evaluation methods include reference-based metrics (such as BLEU and ROUGE), model-based evaluation (LLM-as-a-Judge), and human preference-based evaluation (such as the ELO rating of Chatbot Arena).75% similarUnverifiedUsing automatic metrics for preliminary screening, manual spot checks for calibration, and feeding human feedback back into the reviewer's rules is a viable compromise that balances automated evaluation with human aesthetics.74% similarUnverifiedBLEU and ROUGE are automated evaluation metrics based on reference answers, primarily used for translation or summarization tasks.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129075API
curl https://kongchang.com/api/v1/knowledge/claims/1129075MCP
get_claim(id=1129075)