Alert button
Picture for Gagan Bansal

Gagan Bansal

Alert button

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

Aug 16, 2023
Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, Chi Wang

Figure 1 for AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Figure 2 for AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Figure 3 for AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Figure 4 for AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Viaarxiv icon

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

Jun 08, 2023
Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz

Figure 1 for When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
Figure 2 for When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
Figure 3 for When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
Figure 4 for When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
Viaarxiv icon

Generation Probabilities Are Not Enough: Exploring the Effectiveness of Uncertainty Highlighting in AI-Powered Code Completions

Feb 14, 2023
Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan

Figure 1 for Generation Probabilities Are Not Enough: Exploring the Effectiveness of Uncertainty Highlighting in AI-Powered Code Completions
Figure 2 for Generation Probabilities Are Not Enough: Exploring the Effectiveness of Uncertainty Highlighting in AI-Powered Code Completions
Figure 3 for Generation Probabilities Are Not Enough: Exploring the Effectiveness of Uncertainty Highlighting in AI-Powered Code Completions
Figure 4 for Generation Probabilities Are Not Enough: Exploring the Effectiveness of Uncertainty Highlighting in AI-Powered Code Completions
Viaarxiv icon

Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations

Jan 18, 2023
Valerie Chen, Q. Vera Liao, Jennifer Wortman Vaughan, Gagan Bansal

Figure 1 for Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
Figure 2 for Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
Figure 3 for Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
Figure 4 for Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
Viaarxiv icon

Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers

Oct 29, 2022
Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi-Sangdeh, Han Liu, Saleema Amershi

Figure 1 for Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
Figure 2 for Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
Figure 3 for Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
Figure 4 for Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
Viaarxiv icon

Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

Oct 25, 2022
Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz

Figure 1 for Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
Figure 2 for Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
Figure 3 for Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
Figure 4 for Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
Viaarxiv icon

Using Machine Translation to Localize Task Oriented NLG Output

Jul 09, 2021
Scott Roy, Cliff Brunk, Kyu-Young Kim, Justin Zhao, Markus Freitag, Mihir Kale, Gagan Bansal, Sidharth Mudgal, Chris Varano

Figure 1 for Using Machine Translation to Localize Task Oriented NLG Output
Figure 2 for Using Machine Translation to Localize Task Oriented NLG Output
Figure 3 for Using Machine Translation to Localize Task Oriented NLG Output
Figure 4 for Using Machine Translation to Localize Task Oriented NLG Output
Viaarxiv icon

Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA

Dec 30, 2020
Ana Valeria Gonzalez, Gagan Bansal, Angela Fan, Robin Jia, Yashar Mehdad, Srinivasan Iyer

Figure 1 for Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA
Figure 2 for Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA
Figure 3 for Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA
Figure 4 for Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA
Viaarxiv icon

Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

Jun 30, 2020
Gagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, Daniel S. Weld

Figure 1 for Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Figure 2 for Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Figure 3 for Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Figure 4 for Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Viaarxiv icon