Interaction Quality Assessment on Study 2 Ratings Post-hoc N=4
4.5EnjoymentHuman
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HumanRater Type=Human2026.06 | 4.5 | 4.5 | 4.25 | 3.5 | 3.5 | 3.25 | 4.3 | 4.2 | 2.88 | 6.71 | 6.92 | 2.29 | — | |
| Robot (Inverted Evaluation Framework)Rater Type=Robot (LLM)2026.06 | 4.5 | 4.5 | 4.75 | 1.25 | 4.17 | 4.4 | 4.7 | 4.55 | 2.88 | 6.75 | 7.33 | 1.42 | 2.25 |