Search Results for author:
Found 14 papers, 1 papers with code
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.
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.
Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
While functional correctness is clearly an important property of a code generation model, we argue that it may not fully capture what programmers value when collaborating with their AI pair programmers.
Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
AI code-recommendation systems (CodeRec), such as Copilot, can assist programmers inside an IDE by suggesting and autocompleting arbitrary code; potentially improving their productivity.
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.
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.
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.
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.
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.
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.
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.
