Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.05606 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914573025542144 |
|---|---|
| author | Wang, Ziyi Lu, Yuxuan Li, Wenbo Amini, Amirali Sun, Bo Bart, Yakov Lyu, Weimin Gesi, Jiri Wang, Tian Huang, Jing Su, Yu Ehsan, Upol Alikhani, Malihe Li, Toby Jia-Jun Chilton, Lydia Wang, Dakuo |
| author_facet | Wang, Ziyi Lu, Yuxuan Li, Wenbo Amini, Amirali Sun, Bo Bart, Yakov Lyu, Weimin Gesi, Jiri Wang, Tian Huang, Jing Su, Yu Ehsan, Upol Alikhani, Malihe Li, Toby Jia-Jun Chilton, Lydia Wang, Dakuo |
| contents | Can large language models (LLMs) accurately simulate the next web action of a specific user? While LLMs have shown promising capabilities in generating ``believable'' human behaviors, evaluating their ability to mimic real user behaviors remains an open challenge, largely due to the lack of high-quality, publicly available datasets that capture both the observable actions and the internal reasoning of an actual human user. To address this gap, we introduce OPERA, a novel dataset of Observation, Persona, Rationale, and Action collected from real human participants during online shopping sessions. OPERA is the first public dataset that comprehensively captures: user personas, browser observations, fine-grained web actions, and self-reported just-in-time rationales. We developed both an online questionnaire and a custom browser plugin to gather this dataset with high fidelity. Using OPERA, we establish the first benchmark to evaluate how well current LLMs can predict a specific user's next action and rationale with a given persona and <observation, action, rationale> history. This dataset lays the groundwork for future research into LLM agents that aim to act as personalized digital twins for human. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05606 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation Wang, Ziyi Lu, Yuxuan Li, Wenbo Amini, Amirali Sun, Bo Bart, Yakov Lyu, Weimin Gesi, Jiri Wang, Tian Huang, Jing Su, Yu Ehsan, Upol Alikhani, Malihe Li, Toby Jia-Jun Chilton, Lydia Wang, Dakuo Computation and Language Human-Computer Interaction Can large language models (LLMs) accurately simulate the next web action of a specific user? While LLMs have shown promising capabilities in generating ``believable'' human behaviors, evaluating their ability to mimic real user behaviors remains an open challenge, largely due to the lack of high-quality, publicly available datasets that capture both the observable actions and the internal reasoning of an actual human user. To address this gap, we introduce OPERA, a novel dataset of Observation, Persona, Rationale, and Action collected from real human participants during online shopping sessions. OPERA is the first public dataset that comprehensively captures: user personas, browser observations, fine-grained web actions, and self-reported just-in-time rationales. We developed both an online questionnaire and a custom browser plugin to gather this dataset with high fidelity. Using OPERA, we establish the first benchmark to evaluate how well current LLMs can predict a specific user's next action and rationale with a given persona and <observation, action, rationale> history. This dataset lays the groundwork for future research into LLM agents that aim to act as personalized digital twins for human. |
| title | OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2506.05606 |