Explaining Toxic Text via Knowledge Enhanced Text Generation

By Rohit Sridhar, Diyi Yang. 2022

35 citations recorded by the source corpus.

Warning: This paper contains content that is offensive and may be upsetting.Biased or toxic speech can be harmful to various demographic groups. Therefore, it is not only important for models to detect these speech, but to also output explanations of why a given text is toxic. Previous literature has mostly focused on classifying and detecting toxic speech, and existing efforts on explaining stereotypes in toxic speech mainly use standard text generation approaches, resulting in generic and repetitive explanations. Building on these prior works, we introduce a novel knowledge-informed encoder-decoder framework to utilize multiple knowledge sources to generate implications of biased text.Experiments show that our knowledge informed models outperform prior state-of-the-art models significantly, and can generate detailed explanations of stereotypes in toxic speech compared to baselines, both quantitatively and qualitatively.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Natural Language Processing

Citations in the corpus

Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech (2023, background): “, GPT-2, BART, OPT, and T5 [7, 12, 19]), to create NLEs describing why a given text is considered to be biased [17] or hate-”
GPT (Generative Pre-Trained Transformer)— A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions (2023, background): “GPTs gain their knowledge from a wealth of training data, which includes text taken from the internet, which may be biased, stereotyped, or otherwise offensive [142].”