ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915523271327744 |
|---|---|
| author | Tian, Yuan Zhang, Chuhan Wang, Xiaotong Pan, Sitong Cui, Weiwei Zhang, Haidong Deng, Dazhen Wu, Yingcai |
| author_facet | Tian, Yuan Zhang, Chuhan Wang, Xiaotong Pan, Sitong Cui, Weiwei Zhang, Haidong Deng, Dazhen Wu, Yingcai |
| contents | Creating data reports is a labor-intensive task involving iterative data exploration, insight extraction, and narrative construction. A key challenge lies in composing the analysis logic-from defining objectives and transforming data to identifying and communicating insights. Manually crafting this logic can be cognitively demanding. While experienced analysts often reuse scripts from past projects, finding a perfect match for a new dataset is rare. Even when similar analyses are available online, they usually share only results or visualizations, not the underlying code, making reuse difficult. To address this, we present ReSpark, a system that leverages large language models (LLMs) to reverse-engineer analysis logic from existing reports and adapt it to new datasets. By generating draft analysis steps, ReSpark provides a warm start for users. It also supports interactive refinement, allowing users to inspect intermediate outputs, insert objectives, and revise content. We evaluate ReSpark through comparative and user studies, demonstrating its effectiveness in lowering the barrier to generating data reports without relying on existing analysis code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02329 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMs Tian, Yuan Zhang, Chuhan Wang, Xiaotong Pan, Sitong Cui, Weiwei Zhang, Haidong Deng, Dazhen Wu, Yingcai Human-Computer Interaction Computation and Language Creating data reports is a labor-intensive task involving iterative data exploration, insight extraction, and narrative construction. A key challenge lies in composing the analysis logic-from defining objectives and transforming data to identifying and communicating insights. Manually crafting this logic can be cognitively demanding. While experienced analysts often reuse scripts from past projects, finding a perfect match for a new dataset is rare. Even when similar analyses are available online, they usually share only results or visualizations, not the underlying code, making reuse difficult. To address this, we present ReSpark, a system that leverages large language models (LLMs) to reverse-engineer analysis logic from existing reports and adapt it to new datasets. By generating draft analysis steps, ReSpark provides a warm start for users. It also supports interactive refinement, allowing users to inspect intermediate outputs, insert objectives, and revise content. We evaluate ReSpark through comparative and user studies, demonstrating its effectiveness in lowering the barrier to generating data reports without relying on existing analysis code. |
| title | ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMs |
| topic | Human-Computer Interaction Computation and Language |
| url | https://arxiv.org/abs/2502.02329 |