Unverified50% confidenceFactExact time
The study used conventional reference-based metrics such as BLEU, chrF and TER.
1
Sources
50%
Confidence
Long-term
Relevance
11/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBLEU and ROUGE are automated evaluation metrics based on reference answers, primarily used for translation or summarization tasks.69% similarUnverifiedThe study adopts a dual-track evaluation approach: using BLEU to measure surface similarity and an LLM-based judge to measure semantic similarity.62% similarUnverifiedWhen evaluating "copy or depend," the size of a dependency's transitive closure is a practical reference metric.60% similarUnverifiedThe study validated the automated reference-free metrics using quality ratings from sighted raters and 7 BLV participants, finding a significant correlation between the two.59% similarUnverifiedExact match accuracy requires the generated translation to be completely identical to the reference translation, making it a stricter metric.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1182869API
curl https://kongchang.com/api/v1/knowledge/claims/1182869MCP
get_claim(id=1182869)