1.6k citations · 3k across the 19 of their papers we have counts for
21 papers
AHA!: Facilitating AI Impact Assessment by Generating Examples of Harms
Zana Buçinca, Chau Minh Pham, Maurice Jakesch +3
While demands for change and accountability for harmful AI consequences mount, foreseeing the downstream effects of deploying AI systems remains a challenging task. We developed AH…
Targeted Data Generation: Finding and Fixing Model Weaknesses
Zexue He, Marco Tulio Ribeiro, Fereshte Khani
Even when aggregate accuracy is high, state-of-the-art NLP models often fail systematically on specific subgroups of data, resulting in unfair outcomes and eroding user trust. Addi…
Collaborative Development of NLP models
Fereshte Khani, Marco Tulio Ribeiro
Despite substantial advancements, Natural Language Processing (NLP) models often require post-training adjustments to enforce business rules, rectify undesired behavior, and align…
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan +11
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks,…
Supporting Human-AI Collaboration in Auditing LLMs with LLMs
Charvi Rastogi, Marco Tulio Ribeiro, Nicholas King +2
Large language models are becoming increasingly pervasive and ubiquitous in society via deployment in sociotechnical systems. Yet these language models, be it for classification or…
ART: Automatic multi-step reasoning and tool-use for large language models
Bhargavi Paranjape, Scott Lundberg, Sameer Singh +3
Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings by generating intermediate chain of thought (CoT) reasoning steps. Further, each reasoning…
ScatterShot: Interactive In-context Example Curation for Text Transformation
Tongshuang Wu, Hua Shen, Daniel S. Weld +2
The in-context learning capabilities of LLMs like GPT-3 allow annotators to customize an LLM to their specific tasks with a small number of examples. However, users tend to include…
Editing Models with Task Arithmetic
Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman +4
Changing how pre-trained models behave -- e.g., improving their performance on a downstream task or mitigating biases learned during pre-training -- is a common practice when devel…
Adaptive Testing of Computer Vision Models
Irena Gao, Gabriel Ilharco, Scott Lundberg +1
Vision models often fail systematically on groups of data that share common semantic characteristics (e.g., rare objects or unusual scenes), but identifying these failure modes is…
Fixing Model Bugs with Natural Language Patches
Shikhar Murty, Christopher D. Manning, Scott Lundberg +1
Current approaches for fixing systematic problems in NLP models (e.g. regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In con…
ExSum: From Local Explanations to Model Understanding
Yilun Zhou, Marco Tulio Ribeiro, Julie Shah
Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment. Fulfilling this goal requires bot…
Finding and Fixing Spurious Patterns with Explanations
Gregory Plumb, Marco Tulio Ribeiro, Ameet Talwalkar
Image classifiers often use spurious patterns, such as "relying on the presence of a person to detect a tennis racket, which do not generalize. In this work, we present an end-to-e…
Do Feature Attribution Methods Correctly Attribute Features?
Yilun Zhou, Serena Booth, Marco Tulio Ribeiro +1
Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no…
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models
Tongshuang Wu, Marco Tulio Ribeiro, Jeffrey Heer +1
While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only…
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Gagan Bansal, Tongshuang Wu, Joyce Zhou +5
Many researchers motivate explainable AI with studies showing that human-AI team performance on decision-making tasks improves when the AI explains its recommendations. However, pr…
Beyond Accuracy: Behavioral Testing of NLP models with CheckList
Marco Tulio Ribeiro, Tongshuang Wu, Carlos Guestrin +1
Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches fo…
SQuINTing at VQA Models: Introspecting VQA Models with Sub-Questions
Ramprasaath R. Selvaraju, Purva Tendulkar, Devi Parikh +4
Existing VQA datasets contain questions with varying levels of complexity. While the majority of questions in these datasets require perception for recognizing existence, propertie…
Programs as Black-Box Explanations
Sameer Singh, Marco Tulio Ribeiro, Carlos Guestrin
Recent work in model-agnostic explanations of black-box machine learning has demonstrated that interpretability of complex models does not have to come at the cost of accuracy or m…
Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariance
Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
At the core of interpretable machine learning is the question of whether humans are able to make accurate predictions about a model's behavior. Assumed in this question are three p…
Model-Agnostic Interpretability of Machine Learning
Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to tru…
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which…