Related papers: Removing Spurious Correlation from Neural Network …
Neural network training tends to exploit the simplest features as shortcuts to greedily minimize training loss. However, some of these features might be spuriously correlated with the target labels, leading to incorrect predictions by the…
This paper studies how a centralized planner can modify the structure of a social or information network to reduce polarization. First, polarization is found to be highly dependent on degree and structural properties of the network --…
A trained neural network can be interpreted as a structural causal model (SCM) that provides the effect of changing input variables on the model's output. However, if training data contains both causal and correlational relationships, a…
Consider the problem of estimating the causal effect of some attribute of a text document; for example: what effect does writing a polite vs. rude email have on response time? To estimate a causal effect from observational data, we need to…
Rationalization is fundamental to human reasoning and learning. NLP models trained to produce rationales along with predictions, called self-rationalization models, have been investigated for their interpretability and utility to end-users.…
Learning models have been shown to rely on spurious correlations between non-predictive features and the associated labels in the training data, with negative implications on robustness, bias and fairness. In this work, we provide a…
We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic bias by taking advantage of conditional mutual information.…
In NLP, recent work has seen increased focus on spurious correlations between various features and labels in training data, and how these influence model behavior. However, the presence and effect of such correlations are typically examined…
Causality is omnipresent in scientists' verbalisations of their understanding, even though we have no formal consensual scientific definition for it. In Automata Networks, it suffices to say that automata "influence" one another to…
Understanding predictions made by deep neural networks is notoriously difficult, but also crucial to their dissemination. As all machine learning based methods, they are as good as their training data, and can also capture unwanted biases.…
Much recent work in NLP has documented dataset artifacts, bias, and spurious correlations between input features and output labels. However, how to tell which features have "spurious" instead of legitimate correlations is typically left…
Causal inference studies using textual social media data can provide actionable insights on human behavior. Making accurate causal inferences with text requires controlling for confounding which could otherwise impart bias. Recently, many…
We present a human-in-the-loop dashboard tailored to diagnosing potential spurious features that NLI models rely on for predictions. The dashboard enables users to generate diverse and challenging examples by drawing inspiration from GPT-3…
In this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDIALOG curated in our work. The cur rent models indeed suffer from spurious correlations and have a tendency…
Forecasting conversation derailment can be useful in real-world settings such as online content moderation, conflict resolution, and business negotiations. However, despite language models' success at identifying offensive speech present in…
The presence of spurious features interferes with the goal of obtaining robust models that perform well across many groups within the population. A natural remedy is to remove spurious features from the model. However, in this work we show…
It is often of interest to decompose a total effect of an exposure into the component that acts on the outcome through some mediator and the component that acts independently through other pathways. Said another way, we are interested in…
Learning individual-level causal effects from observational data, such as inferring the most effective medication for a specific patient, is a problem of growing importance for policy makers. The most important aspect of inferring causal…
We propose a set of causal estimands that we call the "mediated probabilities of causation." These estimands quantify the probabilities that an observed negative outcome was induced via a mediating pathway versus a direct pathway in a…
This study investigates the self-rationalization framework constructed with a cooperative game, where a generator initially extracts the most informative segment from raw input, and a subsequent predictor utilizes the selected subset for…