DataScout: Automatic Data Fact Retrieval for Statement Augmentation with an LLM-Based Agent
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913806674821120 |
|---|---|
| author | Chen, Chuer Liu, Yuqi Shi, Danqing Cao, Shixiong Cao, Nan |
| author_facet | Chen, Chuer Liu, Yuqi Shi, Danqing Cao, Shixiong Cao, Nan |
| contents | A data story typically integrates data facts from multiple perspectives and stances to construct a comprehensive and objective narrative. However, retrieving these facts demands time for data search and challenges the creator's analytical skills. In this work, we introduce DataScout, an interactive system that automatically performs reasoning and stance-based data facts retrieval to augment the user's statement. Particularly, DataScout leverages an LLM-based agent to construct a retrieval tree, enabling collaborative control of its expansion between users and the agent. The interface visualizes the retrieval tree as a mind map that eases users to intuitively steer the retrieval direction and effectively engage in reasoning and analysis. We evaluate the proposed system through case studies and in-depth expert interviews. Our evaluation demonstrates that DataScout can effectively retrieve multifaceted data facts from different stances, helping users verify their statements and enhance the credibility of their stories. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17334 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DataScout: Automatic Data Fact Retrieval for Statement Augmentation with an LLM-Based Agent Chen, Chuer Liu, Yuqi Shi, Danqing Cao, Shixiong Cao, Nan Human-Computer Interaction Information Retrieval A data story typically integrates data facts from multiple perspectives and stances to construct a comprehensive and objective narrative. However, retrieving these facts demands time for data search and challenges the creator's analytical skills. In this work, we introduce DataScout, an interactive system that automatically performs reasoning and stance-based data facts retrieval to augment the user's statement. Particularly, DataScout leverages an LLM-based agent to construct a retrieval tree, enabling collaborative control of its expansion between users and the agent. The interface visualizes the retrieval tree as a mind map that eases users to intuitively steer the retrieval direction and effectively engage in reasoning and analysis. We evaluate the proposed system through case studies and in-depth expert interviews. Our evaluation demonstrates that DataScout can effectively retrieve multifaceted data facts from different stances, helping users verify their statements and enhance the credibility of their stories. |
| title | DataScout: Automatic Data Fact Retrieval for Statement Augmentation with an LLM-Based Agent |
| topic | Human-Computer Interaction Information Retrieval |
| url | https://arxiv.org/abs/2504.17334 |