List your company

Human Preference Evaluation on User Study (Conversational Recommendation)

33D2D Preference CountD2D
1.89.91826.1Jun 23, 2026

Evaluation results

MethodLinks
D2DSystem Success Status=Total, Question=Q22026.06331511
D2DSystem Success Status=Total, Question=Q12026.06321710
D2DSystem Success Status=Total, Question=Q32026.06311171
D2DSystem Success Status=D2D Failure (✗), LLM Failure (✗), Question=Q12026.0613700
D2DSystem Success Status=D2D Failure (✗), LLM Failure (✗), Question=Q22026.0613601
D2DSystem Success Status=D2D Failure (✗), LLM Failure (✗), Question=Q32026.0612710
D2DSystem Success Status=D2D Success (✓), LLM Failure (✗), Question=Q12026.0610000
D2DSystem Success Status=D2D Success (✓), LLM Failure (✗), Question=Q22026.0610000
D2DSystem Success Status=D2D Success (✓), LLM Success (✓), Question=Q32026.068200
D2DSystem Success Status=D2D Success (✓), LLM Failure (✗), Question=Q32026.068020
D2DSystem Success Status=D2D Success (✓), LLM Success (✓), Question=Q22026.067210
D2DSystem Success Status=D2D Success (✓), LLM Success (✓), Question=Q12026.066310
D2DSystem Success Status=D2D Failure (✗), LLM Success (✓), Question=Q12026.063700
D2DSystem Success Status=D2D Failure (✗), LLM Success (✓), Question=Q22026.063700
D2DSystem Success Status=D2D Failure (✗), LLM Success (✓), Question=Q32026.063241