WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
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.
Code (0)
등록된 구현이 없습니다.
Tasks
ChatbotSimilar Papers 제목 키워드 기반
Scaling and evaluating sparse autoencoders
Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many con…
Language ModellingNeuro-Visualizer: An Auto-encoder-based Loss Landscape Visualization Method
In recent years, there has been a growing interest in visualizing the loss landscape of neural networks. Linear landscape visualization methods, such as principal component analysis, have become widely used as they intui…
DiME and AGVis: A Distributed Messaging Environment and Geographical Visualizer for Large-scale Power System Simulation
This paper introduces the messaging environment and the geographical visualization tool of the CURENT Large-scale Testbed (LTB) that can be used for large-scale power system closed-loop simulation. First, Distributed Mes…
MidiTok Visualizer: a tool for visualization and analysis of tokenized MIDI symbolic music
Symbolic music research plays a crucial role in music-related machine learning, but MIDI data can be complex for those without musical expertise. To address this issue, we present MidiTok Visualizer, a web application de…
RESIN-EDITOR: A Schema-guided Hierarchical Event Graph Visualizer and Editor
In this paper, we present RESIN-EDITOR, an interactive event graph visualizer and editor designed for analyzing complex events. Our RESIN-EDITOR system allows users to render and freely edit hierarchical event graphs ext…