6 papers
VizCopilot: Fostering Appropriate Reliance on Enterprise Chatbots with Context Visualization
Sam Yu-Te Lee, Jingya Chen, Albert Calzaretto +4
Enterprise chatbots show promise in supporting knowledge workers in information synthesis tasks by retrieving context from large, heterogeneous databases before generating answers.…
Overseeing Agents Without Constant Oversight: Challenges and Opportunities
Madeleine Grunde-McLaughlin, Hussein Mozannar, Maya Murad +3
To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail re…
Magentic-UI: Towards Human-in-the-loop Agentic Systems
Hussein Mozannar, Gagan Bansal, Cheng Tan +17
AI agents powered by large language models are increasingly capable of autonomously completing complex, multi-step tasks using external tools. Yet, they still fall short of human-l…
Steering Language Model Refusal with Sparse Autoencoders
Kyle O'Brien, David Majercak, Xavier Fernandes +7
Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through add…
Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead
Vidhisha Balachandran, Jingya Chen, Lingjiao Chen +8
Inference-time scaling can enhance the reasoning capabilities of large language models (LLMs) on complex problems that benefit from step-by-step problem solving. Although lengtheni…
nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow
Geliang Ouyang, Jingyao Chen, Zhihe Nie +4
Natural Language to Visualization (NL2Vis) seeks to convert natural-language descriptions into visual representations of given tables, empowering users to derive insights from larg…