Filter Results
:
(2,597)
Show Results For
-
All HBS Web
(7,562)
- Faculty Publications (2,597)
Show Results For
-
All HBS Web
(7,562)
- Faculty Publications (2,597)
Modeling →
- 2024
- Conference Paper
Quantifying Uncertainty in Natural Language Explanations of Large Language Models
By: Himabindu Lakkaraju, Sree Harsha Tanneru and Chirag Agarwal
Large Language Models (LLMs) are increasingly used as powerful tools for several
high-stakes natural language processing (NLP) applications. Recent prompting
works claim to elicit intermediate reasoning steps and key tokens that serve as
proxy explanations for LLM...
View Details
Lakkaraju, Himabindu, Sree Harsha Tanneru, and Chirag Agarwal. "Quantifying Uncertainty in Natural Language Explanations of Large Language Models." Paper presented at the Society for Artificial Intelligence and Statistics, 2024.
- January–February 2024
- Article
Shared Service Delivery Can Increase Client Engagement: A Study of Shared Medical Appointments
By: Ryan W. Buell, Kamalini Ramdas, Nazlı Sönmez, Kavitha Srinivasan and Rengaraj Venkatesh
Problem Definition: Clients and service providers alike often consider one-on-one service delivery to be ideal, assuming – perhaps unquestioningly – that devoting individualized attention best improves client outcomes. In contrast, in shared service delivery, clients...
View Details
Keywords:
Health Care and Treatment;
Customer Satisfaction;
Outcome or Result;
Performance Improvement
Buell, Ryan W., Kamalini Ramdas, Nazlı Sönmez, Kavitha Srinivasan, and Rengaraj Venkatesh. "Shared Service Delivery Can Increase Client Engagement: A Study of Shared Medical Appointments." Manufacturing & Service Operations Management 26, no. 1 (January–February 2024): 154–166.
- 2024
- Working Paper
The Impact of Culture Consistency on Subunit Outcomes
By: Jasmijn Bol, Robert Grasser, Serena Loftus and Tatiana Sandino
We examine the association between subunit culture consistency—defined as the
congruence between the organizational values espoused by top management and those
perceived and practiced by subunit employees—and subunit outcomes. Using data
from 235 subunits of a North...
View Details
Bol, Jasmijn, Robert Grasser, Serena Loftus, and Tatiana Sandino. "The Impact of Culture Consistency on Subunit Outcomes." Working Paper, January 2024.
- 2024
- Chapter
The Private Economy Under Party-State Capitalism
By: Margaret M. Pearson, Meg Rithmire and Kellee S. Tsai
This chapter addresses the evolution of China’s approach to the private sector from the early reform era until the beginning of Xi Jinping’s third term. It argues that China has evolved from a familiar form of state capitalism, in which economic growth is the primary...
View Details
Keywords:
Government Administration;
International Relations;
Economic Growth;
Economic Sectors;
Economic Systems;
China
Pearson, Margaret M., Meg Rithmire, and Kellee S. Tsai. "The Private Economy Under Party-State Capitalism." Chap. 3 in Chinese Politics: The Xi Jinping Difference. 2nd edition edited by Stanley Rosen and Daniel C. Lynch, 67–82. Routledge, 2024.
- 2023
- Working Paper
Money, Time, and Grant Design
By: Kyle Myers and Wei Yang Tham
The design of research grants has been hypothesized to be a useful tool for
influencing researchers and their science. We test this by conducting two thought
experiments in a nationally representative survey of academic researchers. First,
we offer participants a...
View Details
Myers, Kyle, and Wei Yang Tham. "Money, Time, and Grant Design." Harvard Business School Working Paper, No. 24-037, December 2023.
- December 2023
- Teaching Note
Buurtzorg
By: Ethan Bernstein and Tatiana Sandino
Teaching Note for HBS Case No. 122-101. As co-founders of home nursing company Buurtzorg, Jos de Blok and Gonnie Kronenberg prized both self-management and organizational learning. Buurtzorg’s 10,000 nurses across 950 neighborhood nursing teams in the Netherlands were...
View Details
- 2023
- Working Paper
Debiasing Treatment Effect Estimation for Privacy-Protected Data: A Model Auditing and Calibration Approach
By: Ta-Wei Huang and Eva Ascarza
Data-driven targeted interventions have become a powerful tool for organizations to optimize business outcomes
by utilizing individual-level data from experiments. A key element of this process is the estimation
of Conditional Average Treatment Effects (CATE), which...
View Details
Huang, Ta-Wei, and Eva Ascarza. "Debiasing Treatment Effect Estimation for Privacy-Protected Data: A Model Auditing and Calibration Approach." Harvard Business School Working Paper, No. 24-034, December 2023.
- 2023
- Article
Balancing Risk and Reward: An Automated Phased Release Strategy
By: Yufan Li, Jialiang Mao and Iavor Bojinov
Phased releases are a common strategy in the technology industry for gradually releasing new products or updates through a sequence of A/B tests in which the number of treated units gradually grows until full deployment or deprecation. Performing phased releases in a...
View Details
Li, Yufan, Jialiang Mao, and Iavor Bojinov. "Balancing Risk and Reward: An Automated Phased Release Strategy." Advances in Neural Information Processing Systems (NeurIPS) (2023).
- 2023
- Article
Benchmarking Large Language Models on CMExam—A Comprehensive Chinese Medical Exam Dataset
By: Junling Liu, Peilin Zhou, Yining Hua, Dading Chong, Zhongyu Tian, Andrew Liu, Helin Wang, Chenyu You, Zhenhua Guo, Lei Zhu and Michael Lingzhi Li
Recent advancements in large language models (LLMs) have transformed the field of question answering (QA). However, evaluating LLMs in the medical field is challenging due to the lack of standardized and comprehensive datasets. To address this gap, we introduce CMExam,...
View Details
Keywords:
Large Language Model;
AI and Machine Learning;
Analytics and Data Science;
Health Industry
Liu, Junling, Peilin Zhou, Yining Hua, Dading Chong, Zhongyu Tian, Andrew Liu, Helin Wang, Chenyu You, Zhenhua Guo, Lei Zhu, and Michael Lingzhi Li. "Benchmarking Large Language Models on CMExam—A Comprehensive Chinese Medical Exam Dataset." Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track 36 (2023).
- December 2023
- Article
Discerning Saints: Moralization of Intrinsic Motivation and Selective Prosociality at Work
By: Mijeong Kwon, Julia Lee Cunningham and Jon M. Jachimowicz
Intrinsic motivation has received widespread attention as a predictor of positive work outcomes, including employees’ prosocial behavior. In the current research, we offer a more nuanced view by proposing that intrinsic motivation does not uniformly increase prosocial...
View Details
Kwon, Mijeong, Julia Lee Cunningham, and Jon M. Jachimowicz. "Discerning Saints: Moralization of Intrinsic Motivation and Selective Prosociality at Work." Academy of Management Journal 66, no. 6 (December 2023): 1625–1650.
- 2023
- Article
M4: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities, and Models
By: Himabindu Lakkaraju, Xuhong Li, Mengnan Du, Jiamin Chen, Yekun Chai and Haoyi Xiong
While Explainable Artificial Intelligence (XAI) techniques have been widely studied to explain predictions made by deep neural networks, the way to evaluate the faithfulness of explanation results remains challenging, due to the heterogeneity of explanations for...
View Details
Keywords:
AI and Machine Learning
Lakkaraju, Himabindu, Xuhong Li, Mengnan Du, Jiamin Chen, Yekun Chai, and Haoyi Xiong. "M4: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities, and Models." Advances in Neural Information Processing Systems (NeurIPS) (2023).
- 2023
- Article
MoPe: Model Perturbation-based Privacy Attacks on Language Models
By: Marvin Li, Jason Wang, Jeffrey Wang and Seth Neel
Recent work has shown that Large Language Models (LLMs) can unintentionally leak sensitive information present in their training data. In this paper, we present Model Perturbations (MoPe), a new method to identify with high confidence if a given text is in the training...
View Details
Li, Marvin, Jason Wang, Jeffrey Wang, and Seth Neel. "MoPe: Model Perturbation-based Privacy Attacks on Language Models." Proceedings of the Conference on Empirical Methods in Natural Language Processing (2023): 13647–13660.
- 2023
- Article
Post Hoc Explanations of Language Models Can Improve Language Models
By: Satyapriya Krishna, Jiaqi Ma, Dylan Slack, Asma Ghandeharioun, Sameer Singh and Himabindu Lakkaraju
Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex tasks. Moreover, recent research has shown that incorporating human-annotated rationales (e.g., Chain-of-Thought prompting) during in-context learning can significantly enhance...
View Details
Krishna, Satyapriya, Jiaqi Ma, Dylan Slack, Asma Ghandeharioun, Sameer Singh, and Himabindu Lakkaraju. "Post Hoc Explanations of Language Models Can Improve Language Models." Advances in Neural Information Processing Systems (NeurIPS) (2023).
- December 2023
- Article
Recover, Explore, Practice: The Transformative Potential of Sabbaticals
By: Kira Schabram, Matt Bloom and DJ DiDonna
Sabbaticals have seen an exponential growth in adoption over the last two decades and are ascribed extensive benefits by employers and employees alike. Little is known, however, about how individuals spend their time or how their experiences impact them after they...
View Details
Schabram, Kira, Matt Bloom, and DJ DiDonna. "Recover, Explore, Practice: The Transformative Potential of Sabbaticals." Academy of Management Discoveries 9, no. 4 (December 2023): 441–468.
- 2023
- Other Article
The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications
By: Mirac Suzgun, Luke Melas-Kyriazi, Suproteem K. Sarkar, Scott Duke Kominers and Stuart Shieber
Innovation is a major driver of economic and social development, and information about many kinds of innovation is embedded in semi-structured data from patents and patent applications. Though the impact and novelty of innovations expressed in patent data are difficult...
View Details
Keywords:
USPTO;
Natural Language Processing;
Classification;
Summarization;
Patent Novelty;
Patent Trolls;
Patent Enforceability;
Patents;
Innovation and Invention;
Intellectual Property;
AI and Machine Learning;
Analytics and Data Science
Suzgun, Mirac, Luke Melas-Kyriazi, Suproteem K. Sarkar, Scott Duke Kominers, and Stuart Shieber. "The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications." Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track 36 (2023).
- November 22, 2023
- Article
Unifying Your Company Around a Moral Goal
By: Ranjay Gulati
In turbulent times, companies need a reliable anchor to guide decision-making. When organizations become moral communities, underpinned by purpose, they provide that stability for stakeholders as well as a reassuring sense of hope, solidarity, agency, and meaning....
View Details
Gulati, Ranjay. "Unifying Your Company Around a Moral Goal." Harvard Business Review Digital Articles (November 22, 2023).
- 2023
- Article
Verifiable Feature Attributions: A Bridge between Post Hoc Explainability and Inherent Interpretability
By: Usha Bhalla, Suraj Srinivas and Himabindu Lakkaraju
With the increased deployment of machine learning models in various real-world applications, researchers and practitioners alike have emphasized the need for explanations of model behaviour. To this end, two broad strategies have been outlined in prior literature to...
View Details
Bhalla, Usha, Suraj Srinivas, and Himabindu Lakkaraju. "Verifiable Feature Attributions: A Bridge between Post Hoc Explainability and Inherent Interpretability." Advances in Neural Information Processing Systems (NeurIPS) (2023).
- December 2023
- Article
What Can Stockouts Tell Us About Inflation? Evidence from Online Micro Data
By: Alberto Cavallo and Oleksiy Kryvtsov
We use a detailed micro dataset on product availability and stockouts to construct a direct high-frequency measure of consumer product shortages during the 2020-2022 pandemic. We document a widespread multi-fold rise in stockouts in nearly all sectors early in the...
View Details
Keywords:
Prices;
Stockouts;
Inventories;
Supply Disruptions;
COVID-19 Pandemic;
Supply Chain;
Product;
Demand and Consumers
Cavallo, Alberto, and Oleksiy Kryvtsov. "What Can Stockouts Tell Us About Inflation? Evidence from Online Micro Data." Journal of International Economics 146 (December 2023).
- December 2023
- Article
When Should the Off-Grid Sun Shine at Night? Optimum Renewable Generation and Energy Storage Investments
By: Christian Kaps, Simone Marinesi and Serguei Netessine
Globally, 1.5 billion people live off the grid, their only access to electricity often limited to operationally-expensive fossil fuel generators. Solar power has risen as a sustainable and less costly option, but its generation is variable during the day and...
View Details
Kaps, Christian, Simone Marinesi, and Serguei Netessine. "When Should the Off-Grid Sun Shine at Night? Optimum Renewable Generation and Energy Storage Investments." Management Science 69, no. 12 (December 2023): 7633–7650.
- 2023
- Article
Which Models Have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness
By: Suraj Srinivas, Sebastian Bordt and Himabindu Lakkaraju
One of the remarkable properties of robust computer vision models is that their input-gradients are often aligned with human perception, referred to in the literature as perceptually-aligned gradients (PAGs). Despite only being trained for classification, PAGs cause...
View Details
Srinivas, Suraj, Sebastian Bordt, and Himabindu Lakkaraju. "Which Models Have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness." Advances in Neural Information Processing Systems (NeurIPS) (2023).