Faithful explanations of black-box nlp models using llm-generated counterfactuals
Causal explanations of the predictions of NLP systems are essential to ensure safety and
establish trust. Yet, existing methods often fall short of explaining model predictions …
establish trust. Yet, existing methods often fall short of explaining model predictions …
Advancing Automated Content Analysis for a New Era of Media Effects Research: The Key Role of Transfer Learning
The availability of individual-level digital trace data offers exciting new ways to study media
uses and effects based on the actual content that people encountered. In this article, we …
uses and effects based on the actual content that people encountered. In this article, we …
Assessing In-context Learning and Fine-tuning for Topic Classification of German Web Data
Researchers in the political and social sciences often rely on classification models to
analyze trends in information consumption by examining browsing histories of millions of …
analyze trends in information consumption by examining browsing histories of millions of …
Hate speech detection using LSTM and explanation by LIME (local interpretable model-agnostic explanations)
RS Tiwari - … Intelligence Methods for Sentiment Analysis in Natural …, 2024 - Elsevier
Abstract Nowadays, Social Media has a very high impact on everyone's lives. Social media
platforms such as Twitter, Facebook, and Instagram are open platforms where people can …
platforms such as Twitter, Facebook, and Instagram are open platforms where people can …