相关论文: Sustainable Modular Debiasing of Language Models

Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but they have also been observed to magnify societal biases, particularly those related to gender. In response to this issue, several…

Artificial intelligence based predictive models trained on the clinical notes can be demographically biased. This could lead to adverse healthcare disparities in predicting outcomes like length of stay of the patients. Thus, it is necessary…

Work on bias in pretrained language models (PLMs) focuses on bias evaluation and mitigation and fails to tackle the question of bias attribution and explainability. We propose a novel metric, the $\textit{bias attribution score}$, which…

In the realms of computer vision and natural language processing, Multimodal Large Language Models (MLLMs) have become indispensable tools, proficient in generating textual responses based on visual inputs. Despite their advancements, our…

This paper presents the LLM-ADE framework, a novel methodology for continued pre-training of large language models (LLMs) that addresses the challenges of catastrophic forgetting and double descent. LLM-ADE employs dynamic architectural…

Social bias in language models can potentially exacerbate social inequalities. Despite it having garnered wide attention, most research focuses on English data. In a low-resource scenario, the models often perform worse due to insufficient…

Multilingual pre-trained language models (PLMs) have demonstrated impressive performance on several downstream tasks for both high-resourced and low-resourced languages. However, there is still a large performance drop for languages unseen…

Structural bias has recently been exploited for aspect sentiment triplet extraction (ASTE) and led to improved performance. On the other hand, it is recognized that explicitly incorporating structural bias would have a negative impact on…

Multimodal emotion recognition in conversations (mERC) is an active research topic in natural language processing (NLP), which aims to predict human's emotional states in communications of multiple modalities, e,g., natural language and…

Pre-trained Language Models (PLMs) exhibit good accuracy and generalization ability across various tasks using self-supervision, but their large size results in high inference latency. Early Exit (EE) strategies handle the issue by allowing…

Despite their impressive performance in a wide range of NLP tasks, Large Language Models (LLMs) have been reported to encode worrying-levels of gender biases. Prior work has proposed debiasing methods that require human labelled examples,…

Social biases can manifest in language agency. However, very limited research has investigated such biases in Large Language Model (LLM)-generated content. In addition, previous works often rely on string-matching techniques to identify…

The recent breakthrough of large language models (LLMs) in natural language processing has sparked exploration in recommendation systems, however, their limited domain-specific knowledge remains a critical bottleneck. Specifically, LLMs…

Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the…

Gender-bias stereotypes have recently raised significant ethical concerns in natural language processing. However, progress in detection and evaluation of gender bias in natural language understanding through inference is limited and…

Large language models (LLMs) have achieved impressive performance on various natural language generation tasks. Nonetheless, they suffer from generating negative and harmful contents that are biased against certain demographic groups (e.g.,…

Multimodal Large Language Models (MLLMs) have shown substantial capabilities in integrating visual and textual information, yet frequently rely on spurious correlations, undermining their robustness and generalization in complex multimodal…

We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization…

Language Model pre-training uses broad data mixtures to enhance performance across domains and languages. However, training on such heterogeneous text corpora requires extensive and expensive efforts. Since these data sources vary…

In this project, we want to explore the newly emerging field of prompt engineering and apply it to the downstream task of detecting LM biases. More concretely, we explore how to design prompts that can indicate 4 different types of biases:…