Publications
Publications
Show Results For
- All HBS Web
(123)
- Faculty Publications (15)
Page 1 of 15
Results
- 2024
- Working Paper
The Narrative AI Advantage? A Field Experiment on Generative AI-Augmented Evaluations of Early-Stage Innovations
By: Jacqueline N. Lane, Léonard Boussioux, Charles Ayoubi, Ying Hao Chen, Camila Lin, Rebecca Spens, Pooja Wagh and Pei-Hsin Wang
The rise of generative artificial intelligence (AI) is transforming creative problem-solving, necessitating new approaches for evaluating innovative solutions. This study explores how human-AI collaboration can enhance early-stage evaluations, focusing on the interplay... View Details
- 2022
- Working Paper
Racial Diversity in Private Capital Fundraising
By: Johan Cassel, Josh Lerner and Emmanuel Yimfor
Black- and Hispanic-owned funds control a very modest share of assets in the private capital
industry. We find that the sensitivity of follow-on fundraising to fund performance
is greater for minority-owned groups, particularly for underperforming groups. We... View Details
- 2022
- Conference Presentation
Towards the Unification and Robustness of Post hoc Explanation Methods
By: Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Steven Wu and Himabindu Lakkaraju
As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a post hoc manner. In this work, we analyze two... View Details
Keywords: AI and Machine Learning
- Article
Reliable Post hoc Explanations: Modeling Uncertainty in Explainability
By: Dylan Slack, Sophie Hilgard, Sameer Singh and Himabindu Lakkaraju
As black box explanations are increasingly being employed to establish model credibility in high stakes settings, it is important to ensure that these explanations are accurate and reliable. However, prior work demonstrates that explanations generated by... View Details
- Article
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
By: Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Steven Wu and Himabindu Lakkaraju
As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a post hoc manner. In this work, we analyze two... View Details
- Article
Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses
By: Kaivalya Rawal and Himabindu Lakkaraju
As predictive models are increasingly being deployed in high-stakes decision-making, there has been a lot of interest in developing algorithms which can provide recourses to affected individuals. While developing such tools is important, it is even more critical to... View Details
- Article
Robust and Stable Black Box Explanations
By: Himabindu Lakkaraju, Nino Arsov and Osbert Bastani
As machine learning black boxes are increasingly being deployed in real-world applications, there
has been a growing interest in developing post hoc explanations that summarize the behaviors
of these black boxes. However, existing algorithms for generating such... View Details
- 2020
- Article
'How Do I Fool You?': Manipulating User Trust via Misleading Black Box Explanations
By: Himabindu Lakkaraju and Osbert Bastani
- Article
Faithful and Customizable Explanations of Black Box Models
By: Himabindu Lakkaraju, Ece Kamar, Rich Caruana and Jure Leskovec
As predictive models increasingly assist human experts (e.g., doctors) in day-to-day decision making, it is crucial for experts to be able to explore and understand how such models behave in different feature subspaces in order to know if and when to trust them. To... View Details
- August 2017 (Revised July 2018)
- Case
MannKind Corporation: Take a Deep Breath, This Time Afrezza Will Work
By: Elie Ofek and Amanda Dai
In June 2014, MannKind Corporation announced that after years of development and billions of dollars in expenses, the FDA had finally approved its drug, Afrezza. MannKind would thus be the only company with an inhalable insulin on the market. As an alternative to... View Details
- October 2010 (Revised November 2010)
- Background Note
Plavix: Drugs in the Age of Personalized Medicine
By: Richard G. Hamermesh, Mara G. Aspinall and Rachel Gordon
PIavix, one of the world's best selling drugs in 2010, appears to have a limited future. Its patent was due to expire soon, and recently new data had been discovered that indicated that a small subset of the population would be at risk for stroke, heart attack, or even... View Details
- October 2008
- Article
Organizational Responses to Environmental Demands: Opening the Black Box
By: Magali Delmas and Michael W. Toffel
This paper combines new and old institutionalism to explain differences in organizational strategies. We propose that differences in the influence of corporate departments lead their facilities to prioritize different external pressures and thus adopt different... View Details
- 2001
- Article
From Guilford to Creative Synergy: Opening the Black Box of Team Level Creativity
By: T. R. Kurtzberg and T. M. Amabile
Previous research, from Guilford's founding tradition to more modern research on individual creativity and general group processes, falls short of adequately describing team-level creativity. Alhough researchers have addressed brainstorming in groups with mixed... View Details
- 14 Aug 2017
- Conference Presentation
Interpretable and Explorable Approximations of Black Box Models
By: Himabindu Lakkaraju, Ece Kamar, Rich Caruana and Jure Leskovec
- Teaching Interest
Large-Scale Investment (LSI, MBA Elective Curriculum)
By: Benjamin C. Esty
Large-Scale Investment (LSI) is a case-based course about project finance that is designed for second-year MBA students. Project finance involves the creation of a legally independent project company financed with nonrecourse debt for the purpose of investing in a... View Details