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.
no code implementations • 11 Oct 2023 • Ariel Goldstein, Eric Ham, Mariano Schain, Samuel Nastase, Zaid Zada, Avigail Dabush, Bobbi Aubrey, Harshvardhan Gazula, Amir Feder, Werner K Doyle, Sasha Devore, Patricia Dugan, Daniel Friedman, Roi Reichart, Michael Brenner, Avinatan Hassidim, Orrin Devinsky, Adeen Flinker, Omer Levy, Uri Hasson
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.
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.
(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.
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.
Our causal framework and our results demonstrate the importance of studying datasets and the benefits of causality for understanding NLP models.
Accurately predicting the relevance of items to users is crucial to the success of many social platforms.
We introduce CEBaB, a new benchmark dataset for assessing concept-based explanation methods in Natural Language Processing (NLP).
Natural language processing (NLP) algorithms have become very successful, but they still struggle when applied to out-of-distribution examples.
1 code implementation • 2 Sep 2021 • Amir Feder, Katherine A. Keith, Emaad Manzoor, Reid Pryzant, Dhanya Sridhar, Zach Wood-Doughty, Jacob Eisenstein, Justin Grimmer, Roi Reichart, Margaret E. Roberts, Brandon M. Stewart, Victor Veitch, Diyi Yang
A fundamental goal of scientific research is to learn about causal relationships.
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.
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.
Recent improvements in the predictive quality of natural language processing systems are often dependent on a substantial increase in the number of model parameters.
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.
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.
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.