Search Results for author:
Found 16 papers, 3 papers with code
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks.
Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
However, to fully realize their potential, we must understand how programmers interact with these systems and identify ways to improve that interaction.
When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
Using data from 535 programmers, we perform a retrospective evaluation of CDHF and show that we can avoid displaying a significant fraction of suggestions that would have been rejected.
The Challenge of Crafting Intelligible Intelligence
Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to understand.
Revenue Forecasting for Enterprise Products
For any business, planning is a continuous process, and typically business-owners focus on making both long-term planning aligned with a particular strategy as well as short-term planning that accommodates the dynamic market situations.
Gmail Smart Compose: Real-Time Assisted Writing
In this paper, we present Smart Compose, a novel system for generating interactive, real-time suggestions in Gmail that assists users in writing mails by reducing repetitive typing.
A Case for Backward Compatibility for Human-AI Teams
We introduce the notion of the compatibility of an AI update with prior user experience and present methods for studying the role of compatibility in human-AI teams.
Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork
To optimize the team performance for this setting we maximize the team's expected utility, expressed in terms of the quality of the final decision, cost of verifying, and individual accuracies of people and machines.
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
However, prior studies observed improvements from explanations only when the AI, alone, outperformed both the human and the best team.
Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA
While research on explaining predictions of open-domain QA systems (ODQA) to users is gaining momentum, most works have failed to evaluate the extent to which explanations improve user trust.
Using Machine Translation to Localize Task Oriented NLG Output
One of the challenges in a task oriented natural language application like the Google Assistant, Siri, or Alexa is to localize the output to many languages.
Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
Large language models have demonstrated great potential to assist programmers in generating code.
Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
AI explanations are often mentioned as a way to improve human-AI decision-making, but empirical studies have not found consistent evidence of explanations' effectiveness and, on the contrary, suggest that they can increase overreliance when the AI system is wrong.
Generation Probabilities Are Not Enough: Exploring the Effectiveness of Uncertainty Highlighting in AI-Powered Code Completions
Through a mixed-methods study with 30 programmers, we compare three conditions: providing the AI system's code completion alone, highlighting tokens with the lowest likelihood of being generated by the underlying generative model, and highlighting tokens with the highest predicted likelihood of being edited by a programmer.
