Unverified50% confidenceFactExact time
Deletion testing evaluates explanation faithfulness by masking the regions highlighted by the explanation and observing the degree of drop in model confidence.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe study found that the faithfulness of deletion-based explanations is highly coupled with the detection strength at the time of explanation generation.75% similarUnverified理想的评估流程应将仿真评估作为初筛工具排除明显不合格的策略，再通过真实世界物理测试完成最终验证73% similarUnverifiedThe evaluation framework for this experiment adopts an anti-cheating public evaluation approach featuring timestamp locking, non-deletable results, constant comparison against paired baselines, and explicit labeling of statistical significance and sample limitations.72% similarUnverifiedBefore evaluation, it is essential to verify that the test framework has genuinely scored every row it claims to have evaluated; otherwise, scripts that silently swallow errors will produce a false 100% pass rate that excludes the hardest edge cases.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975879API
curl https://kongchang.com/api/v1/knowledge/claims/975879MCP
get_claim(id=975879)