Broadening Access to Simulations for End-Users via Large Language Models: Challenges and Opportunities
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912041988521984 |
|---|---|
| author | Giabbanelli, Philippe J. Padilla, Jose J. Agrawal, Ameeta |
| author_facet | Giabbanelli, Philippe J. Padilla, Jose J. Agrawal, Ameeta |
| contents | Large Language Models (LLMs) are becoming ubiquitous to create intelligent virtual assistants that assist users in interacting with a system, as exemplified in marketing. Although LLMs have been discussed in Modeling & Simulation (M&S), the community has focused on generating code or explaining results. We examine the possibility of using LLMs to broaden access to simulations, by enabling non-simulation end-users to ask what-if questions in everyday language. Specifically, we discuss the opportunities and challenges in designing such an end-to-end system, divided into three broad phases. First, assuming the general case in which several simulation models are available, textual queries are mapped to the most relevant model. Second, if a mapping cannot be found, the query can be automatically reformulated and clarifying questions can be generated. Finally, simulation results are produced and contextualized for decision-making. Our vision for such system articulates long-term research opportunities spanning M&S, LLMs, information retrieval, and ethics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15290 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Broadening Access to Simulations for End-Users via Large Language Models: Challenges and Opportunities Giabbanelli, Philippe J. Padilla, Jose J. Agrawal, Ameeta Human-Computer Interaction Artificial Intelligence Large Language Models (LLMs) are becoming ubiquitous to create intelligent virtual assistants that assist users in interacting with a system, as exemplified in marketing. Although LLMs have been discussed in Modeling & Simulation (M&S), the community has focused on generating code or explaining results. We examine the possibility of using LLMs to broaden access to simulations, by enabling non-simulation end-users to ask what-if questions in everyday language. Specifically, we discuss the opportunities and challenges in designing such an end-to-end system, divided into three broad phases. First, assuming the general case in which several simulation models are available, textual queries are mapped to the most relevant model. Second, if a mapping cannot be found, the query can be automatically reformulated and clarifying questions can be generated. Finally, simulation results are produced and contextualized for decision-making. Our vision for such system articulates long-term research opportunities spanning M&S, LLMs, information retrieval, and ethics. |
| title | Broadening Access to Simulations for End-Users via Large Language Models: Challenges and Opportunities |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2409.15290 |