List your company

Reference-free Conversation Evaluation on CRSArena-Eval RD

0.712Pearson Correlation (r)FACE
0.076560.241530.40650.57147May 30, 2025

Evaluation results

MethodLinks
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.7120.668
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.650.635
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.6170.555
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.6050.574
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.5770.577
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.570.453
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.5640.522
FACEBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.5510.53
FACEBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.5490.55
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.5220.482
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.4980.472
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.490.471
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.490.444
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.4880.482
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.4840.534
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.4820.392
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.4810.457
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.4680.462
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.4640.455
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.4530.446
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.4470.43
FACEBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.4430.437
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.4330.422
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.4320.422
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.4250.4
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.4050.363
UniEvalLevel=Dialogue-level, Aspect=Overall impression2025.050.3950.387
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.360.341
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.3510.364
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.3420.329
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.3390.423
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.3320.325
UniEvalLevel=Turn-level, Aspect=Relevance2025.050.3110.288
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.3020.289
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.2790.29
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.2480.26
UniEvalLevel=Dialogue-level, Aspect=Understanding2025.050.2460.225
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.2350.255
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.2170.203
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.1880.174
UniEvalLevel=Turn-level, Aspect=Interestingness2025.050.1820.242
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.1750.177
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.1740.174
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.1010.101