WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909308541730816 |
|---|---|
| author | Deng, Yuntian Zhao, Wenting Hessel, Jack Ren, Xiang Cardie, Claire Choi, Yejin |
| author_facet | Deng, Yuntian Zhao, Wenting Hessel, Jack Ren, Xiang Cardie, Claire Choi, Yejin |
| contents | The increasing availability of real-world conversation data offers exciting opportunities for researchers to study user-chatbot interactions. However, the sheer volume of this data makes manually examining individual conversations impractical. To overcome this challenge, we introduce WildVis, an interactive tool that enables fast, versatile, and large-scale conversation analysis. WildVis provides search and visualization capabilities in the text and embedding spaces based on a list of criteria. To manage million-scale datasets, we implemented optimizations including search index construction, embedding precomputation and compression, and caching to ensure responsive user interactions within seconds. We demonstrate WildVis' utility through three case studies: facilitating chatbot misuse research, visualizing and comparing topic distributions across datasets, and characterizing user-specific conversation patterns. WildVis is open-source and designed to be extendable, supporting additional datasets and customized search and visualization functionalities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_03753 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild Deng, Yuntian Zhao, Wenting Hessel, Jack Ren, Xiang Cardie, Claire Choi, Yejin Computation and Language Artificial Intelligence Human-Computer Interaction Information Retrieval Machine Learning The increasing availability of real-world conversation data offers exciting opportunities for researchers to study user-chatbot interactions. However, the sheer volume of this data makes manually examining individual conversations impractical. To overcome this challenge, we introduce WildVis, an interactive tool that enables fast, versatile, and large-scale conversation analysis. WildVis provides search and visualization capabilities in the text and embedding spaces based on a list of criteria. To manage million-scale datasets, we implemented optimizations including search index construction, embedding precomputation and compression, and caching to ensure responsive user interactions within seconds. We demonstrate WildVis' utility through three case studies: facilitating chatbot misuse research, visualizing and comparing topic distributions across datasets, and characterizing user-specific conversation patterns. WildVis is open-source and designed to be extendable, supporting additional datasets and customized search and visualization functionalities. |
| title | WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2409.03753 |