Search Results for author:
Found 17 papers, 8 papers with code
Learning and Evaluating a Differentially Private Pre-trained Language Model
One method to guarantee the privacy of such individuals is to train a differentially-private language model, but this usually comes at the expense of model performance.
The Temporal Structure of Language Processing in the Human Brain Corresponds to The Layered Hierarchy of Deep Language Models
Our results reveal a connection between human language processing and DLMs, with the DLM's layer-by-layer accumulation of contextual information mirroring the timing of neural activity in high-order language areas.
Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
We hence present a second approach based on matching, and propose a method that is guided by an LLM at training-time and learns a dedicated embedding space.
Evaluating the Moral Beliefs Encoded in LLMs
(2) We apply this method to study what moral beliefs are encoded in different LLMs, especially in ambiguous cases where the right choice is not obvious.
An Invariant Learning Characterization of Controlled Text Generation
In this paper, we show that the performance of controlled generation may be poor if the distributions of text in response to user prompts differ from the distribution the predictor was trained on.
Useful Confidence Measures: Beyond the Max Score
An important component in deploying machine learning (ML) in safety-critic applications is having a reliable measure of confidence in the ML model's predictions.
Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions
Our causal framework and our results demonstrate the importance of studying datasets and the benefits of causality for understanding NLP models.
In the Eye of the Beholder: Robust Prediction with Causal User Modeling
Accurately predicting the relevance of items to users is crucial to the success of many social platforms.
CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
We introduce CEBaB, a new benchmark dataset for assessing concept-based explanation methods in Natural Language Processing (NLP).
DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation
Natural language processing (NLP) algorithms have become very successful, but they still struggle when applied to out-of-distribution examples.
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
A fundamental goal of scientific research is to learn about causal relationships.
Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions
Deep learning algorithms have shown promising results in visual question answering (VQA) tasks, but a more careful look reveals that they often do not understand the rich signal they are being fed with.
On Calibration and Out-of-domain Generalization
In this work, we draw a link between OOD performance and model calibration, arguing that calibration across multiple domains can be viewed as a special case of an invariant representation leading to better OOD generalization.
Model Compression for Domain Adaptation through Causal Effect Estimation
Recent improvements in the predictive quality of natural language processing systems are often dependent on a substantial increase in the number of model parameters.
CausaLM: Causal Model Explanation Through Counterfactual Language Models
Concretely, we show that by carefully choosing auxiliary adversarial pre-training tasks, language representation models such as BERT can effectively learn a counterfactual representation for a given concept of interest, and be used to estimate its true causal effect on model performance.
Predicting In-game Actions from Interviews of NBA Players
We find that our best performing textual model is most associated with topics that are intuitively related to each prediction task and that better models yield higher correlation with more informative topics.
Explaining Classifiers with Causal Concept Effect (CaCE)
To overcome this problem, we define the Causal Concept Effect (CaCE) as the causal effect of (the presence or absence of) a human-interpretable concept on a deep neural net's predictions.
