Publications
Publications
Show Results For
- All HBS Web
(319)
- Faculty Publications (78)
Page 1 of 78
Results →
- 2024
- Working Paper
Empirical Guidance: Data Processing and Analysis with Applications in Stata, R, and Python
By: Melissa Ouellet and Michael W. Toffel
This paper describes a range of best practices to compile and analyze datasets, and includes some examples in Stata, R, and Python. It is meant to serve as a reference for those getting started in econometrics, and especially those seeking to conduct data analyses in... View Details
- July–August 2024
- Article
Doing More with Less: Overcoming Ineffective Long-Term Targeting Using Short-Term Signals
By: Ta-Wei Huang and Eva Ascarza
Firms are increasingly interested in developing targeted interventions for customers with the best response,
which requires identifying differences in customer sensitivity, typically through the conditional average treatment
effect (CATE) estimation. In theory, to... View Details
- 2023
- Working Paper
An Experimental Design for Anytime-Valid Causal Inference on Multi-Armed Bandits
By: Biyonka Liang and Iavor I. Bojinov
Typically, multi-armed bandit (MAB) experiments are analyzed at the end of the study and thus require the analyst to specify a fixed sample size in advance. However, in many online learning applications, it is advantageous to continuously produce inference on the... View Details
- 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
- 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
- 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
- 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
- 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
- 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
- Working Paper
An AI Method to Score Celebrity Visual Potential from Human Faces
By: Flora Feng, Shunyuan Zhang, Xiao Liu, Kannan Srinivasan and Cait Lamberton
Celebrities have extraordinary abilities to attract and influence others. Predicting celebrity visual potential is important in the domains of business, politics, media, and entertainment. Can we use human faces to predict celebrity visual potential? If so, which... View Details
- October 2023
- Article
Improving Regulatory Effectiveness Through Better Targeting: Evidence from OSHA
By: Matthew S. Johnson, David I. Levine and Michael W. Toffel
We study how a regulator can best target inspections. Our case study is a U.S. Occupational Safety and Health Administration (OSHA) program that randomly allocated some inspections. On average, each inspection averted 2.4 serious injuries (9%) over the next five years.... View Details
- 2023
- Working Paper
In-Context Unlearning: Language Models as Few Shot Unlearners
By: Martin Pawelczyk, Seth Neel and Himabindu Lakkaraju
Machine unlearning, the study of efficiently removing the impact of specific training points on the
trained model, has garnered increased attention of late, driven by the need to comply with privacy
regulations like the Right to be Forgotten. Although unlearning is... View Details
- August 2023
- Article
Explaining Machine Learning Models with Interactive Natural Language Conversations Using TalkToModel
By: Dylan Slack, Satyapriya Krishna, Himabindu Lakkaraju and Sameer Singh
Practitioners increasingly use machine learning (ML) models, yet models have become more complex and harder to understand. To understand complex models, researchers have proposed techniques to explain model predictions. However, practitioners struggle to use... View Details
- 2023
- Article
Towards Bridging the Gaps between the Right to Explanation and the Right to Be Forgotten
By: Himabindu Lakkaraju, Satyapriya Krishna and Jiaqi Ma
The Right to Explanation and the Right to be Forgotten are two important principles outlined to regulate algorithmic decision making and data usage in real-world applications. While the right to explanation allows individuals to request an actionable explanation for an... View Details
- 2023
- Working Paper
Insufficiently Justified Disparate Impact: A New Criterion for Subgroup Fairness
By: Neil Menghani, Edward McFowland III and Daniel B. Neill
In this paper, we develop a new criterion, "insufficiently justified disparate impact" (IJDI), for assessing whether recommendations (binarized predictions) made by an algorithmic decision support tool are fair. Our novel, utility-based IJDI criterion evaluates false... View Details
- 2023
- Working Paper
Auditing Predictive Models for Intersectional Biases
By: Kate S. Boxer, Edward McFowland III and Daniel B. Neill
Predictive models that satisfy group fairness criteria in aggregate for members of a protected class, but do not guarantee subgroup fairness, could produce biased predictions for individuals at the intersection of two or more protected classes. To address this risk, we... View Details
- 2023
- Article
Exploiting Discovered Regression Discontinuities to Debias Conditioned-on-observable Estimators
By: Benjamin Jakubowski, Siram Somanchi, Edward McFowland III and Daniel B. Neill
Regression discontinuity (RD) designs are widely used to estimate causal effects in the absence of a randomized experiment. However, standard approaches to RD analysis face two significant limitations. First, they require a priori knowledge of discontinuities in... View Details
- 2023
- Article
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
By: Martin Pawelczyk, Teresa Datta, Johannes van-den-Heuvel, Gjergji Kasneci and Himabindu Lakkaraju
As machine learning models are increasingly being employed to make consequential decisions in real-world settings, it becomes critical to ensure that individuals who are adversely impacted (e.g., loan denied) by the predictions of these models are provided with a means... View Details
- 2024
- Working Paper
Using LLMs for Market Research
By: James Brand, Ayelet Israeli and Donald Ngwe
Large language models (LLMs) have rapidly gained popularity as labor-augmenting
tools for programming, writing, and many other processes that benefit from quick text
generation. In this paper we explore the uses and benefits of LLMs for researchers and
practitioners... View Details
- 2023
- Working Paper
Feature Importance Disparities for Data Bias Investigations
By: Peter W. Chang, Leor Fishman and Seth Neel
It is widely held that one cause of downstream bias in classifiers is bias present in the training data. Rectifying such biases may involve context-dependent interventions such as training separate models on subgroups, removing features with bias in the collection... View Details