Gaze patterns predict preference and confidence in pairwise AI image evaluation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914422717415424 |
|---|---|
| author | Papadopoulos, Nikolas Navaneethan, Shreenithi Bai, Sheng Samanta, Ankur Sajda, Paul |
| author_facet | Papadopoulos, Nikolas Navaneethan, Shreenithi Bai, Sheng Samanta, Ankur Sajda, Paul |
| contents | Preference learning methods, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on pairwise human judgments, yet little is known about the cognitive processes underlying these judgments. We investigate whether eye-tracking can reveal preference formation during pairwise AI-generated image evaluation. Thirty participants completed 1,800 trials while their gaze was recorded. We replicated the gaze cascade effect, with gaze shifting toward chosen images approximately one second before the decision. Cascade dynamics were consistent across confidence levels. Gaze features predicted binary choice (68% accuracy), with chosen images receiving more dwell time, fixations, and revisits. Gaze transitions distinguished high-confidence from uncertain decisions (66% accuracy), with low-confidence trials showing more image switches per second. These results show that gaze patterns predict both choice and confidence in pairwise image evaluations, suggesting that eye-tracking provides implicit signals relevant to the quality of preference annotations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24849 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Gaze patterns predict preference and confidence in pairwise AI image evaluation Papadopoulos, Nikolas Navaneethan, Shreenithi Bai, Sheng Samanta, Ankur Sajda, Paul Human-Computer Interaction Artificial Intelligence Computer Vision and Pattern Recognition Computers and Society Preference learning methods, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on pairwise human judgments, yet little is known about the cognitive processes underlying these judgments. We investigate whether eye-tracking can reveal preference formation during pairwise AI-generated image evaluation. Thirty participants completed 1,800 trials while their gaze was recorded. We replicated the gaze cascade effect, with gaze shifting toward chosen images approximately one second before the decision. Cascade dynamics were consistent across confidence levels. Gaze features predicted binary choice (68% accuracy), with chosen images receiving more dwell time, fixations, and revisits. Gaze transitions distinguished high-confidence from uncertain decisions (66% accuracy), with low-confidence trials showing more image switches per second. These results show that gaze patterns predict both choice and confidence in pairwise image evaluations, suggesting that eye-tracking provides implicit signals relevant to the quality of preference annotations. |
| title | Gaze patterns predict preference and confidence in pairwise AI image evaluation |
| topic | Human-Computer Interaction Artificial Intelligence Computer Vision and Pattern Recognition Computers and Society |
| url | https://arxiv.org/abs/2603.24849 |