Advances in Emotion Recognition and Bias Mitigation in Language Models

The field of natural language processing is moving towards a more nuanced understanding of emotions and biases in language models. Recent research has focused on developing more effective methods for emotion recognition, including multi-task learning approaches that incorporate emotional dimensions and label distribution learning for mixed emotion recognition. Additionally, there is a growing concern about bias in language models, with studies investigating the unintended consequences of targeted bias mitigation and proposing new methods for reducing social biases. Noteworthy papers in this area include:

  • A study on Empathetic Cascading Networks, which presents a multi-stage prompting method for enhancing empathetic capabilities in large language models.
  • A paper on Emotion-Enhanced Multi-Task Learning, which introduces a novel framework for joint learning of sentiment polarity and category-specific emotions.
  • Research on No Free Lunch in Language Model Bias Mitigation, which highlights the potential negative consequences of targeted bias mitigation and emphasizes the need for robust evaluation tools.

Sources

GeeSanBhava: Sentiment Tagged Sinhala Music Video Comment Data Set

No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases

Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models

Emotion-Enhanced Multi-Task Learning with LLMs for Aspect Category Sentiment Analysis

Gender Bias in Emotion Recognition by Large Language Models

Language-Independent Sentiment Labelling with Distant Supervision: A Case Study for English, Sepedi and Setswana

Prompt Fairness: Sub-group Disparities in LLMs

EM2LDL: A Multilingual Speech Corpus for Mixed Emotion Recognition through Label Distribution Learning

Built with on top of