List your company

Reference-free Conversation Evaluation on CRSArena-Eval KG

0.766Pearson Correlation (r)FACE
0.087920.263960.440.61604May 30, 2025

Evaluation results

MethodLinks
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.7660.679
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.7190.677
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.6720.557
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.6640.611
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.6560.642
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.6550.557
UniEvalLevel=Dialogue-level, Aspect=Overall impression2025.050.6180.659
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.5990.546
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Overall impression2025.050.5990.521
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.5930.484
FACEBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.580.538
UniEvalLevel=Dialogue-level, Aspect=Understanding2025.050.5630.541
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.5620.52
FACEBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.5430.527
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.5380.481
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Understanding2025.050.5350.475
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.5330.505
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.5180.543
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.4920.486
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.4850.463
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.4850.461
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.4750.434
FACEBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.4710.453
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.4520.452
FACEBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.4490.404
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.4430.447
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.4350.397
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.430.422
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Task completion2025.050.4260.411
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.4250.378
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.4240.403
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Relevance2025.050.4190.408
UniEvalLevel=Turn-level, Aspect=Relevance2025.050.4160.428
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=All, Aspect=All2025.050.3830.352
G-EvalBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.3340.316
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.3090.279
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.3080.324
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Interest arousal2025.050.2970.322
UniEvalLevel=Turn-level, Aspect=Interestingness2025.050.2620.401
FACE w/o trainBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.240.419
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.2380.231
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Turn-level, Aspect=Interestingness2025.050.2030.19
LLMDirectBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.1370.137
LLMCoT+ICLBackbone=Llama-3.1-8B-Instruct, Level=Dialogue-level, Aspect=Efficiency2025.050.1140.114