Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Tool Learning under Instruction with Missing Key Information on NoisyToolBench IMKI 1.0 (test)

94A1 Success Rate

CoT + AwN

-3.7621.624772.38Aug 31, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.08
946250
2024.08
905836
2024.08
885246
2024.08
886046
2024.08
864018
2024.08
866242
2024.08
821616
2024.08
824012
2024.08
805648
2024.08
805452
2024.08
805234
2024.08
785452
2024.08
743622
2024.08
744424
2024.08
744832
2024.08
725242
2024.08
705236
2024.08
641612
2024.08
6222
2024.08
582018
2024.08
545050
2024.08
524834
2024.08
524442
2024.08
444020
2024.08
423026
2024.08
261814
2024.08
242620
2024.08
221810
2024.08
102216
2024.08
22018
2024.08
01616
2024.08
01616