Related papers: Mitigating Bias in Text Classification via Prompt-…

Recent advancements in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation.…

Online news platforms commonly employ personalized news recommendation methods to assist users in discovering interesting articles, and many previous works have utilized language model techniques to capture user interests and understand…

In prompt tuning, a prefix or suffix text is added to the prompt, and the embeddings (soft prompts) or token indices (hard prompts) of the prefix/suffix are optimized to gain more control over language models for specific tasks. This…

(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation…

This study explores the integration of a representative large language model, ChatGPT, into lending decision-making with a focus on credit default prediction. Specifically, we use ChatGPT to analyse and interpret loan assessments written by…

Supervised machine learning models and their evaluation strongly depends on the quality of the underlying dataset. When we search for a relevant piece of information it may appear anywhere in a given passage. However, we observe a bias in…

Facilitated by large language models (LLMs), personalized text generation has become a rapidly growing research direction. Most existing studies focus on designing specialized models for a particular domain, or they require fine-tuning the…

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…

Language models are known to absorb biases from their training data, leading to predictions driven by statistical regularities rather than semantic relevance. We investigate the impact of these biases on answer choice preferences in the…

Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization…

Text-to-Image (TTI) models generate images based on text prompts, which often leave certain aspects of the desired image ambiguous. When faced with these ambiguities, TTI models have been shown to exhibit biases in their interpretations.…

Addressing biases in computer vision models is crucial for real-world AI deployments. However, mitigating visual biases is challenging due to their unexplainable nature, often identified indirectly through visualization or sample…

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an…

With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning regards selecting appropriate keywords included into the input,…

The proliferation of NLP-powered language technologies, AI-based natural language generation models, and English as a mainstream means of communication among both native and non-native speakers make the output of AI-powered tools especially…

As the breadth and depth of language model applications continue to expand rapidly, it is increasingly important to build efficient frameworks for measuring and mitigating the learned or inherited social biases of these models. In this…

Writing effective prompts for large language models (LLM) can be unintuitive and burdensome. In response, services that optimize or suggest prompts have emerged. While such services can reduce user effort, they also introduce a risk: the…

Modeling topics effectively in short texts, such as tweets and news snippets, is crucial to capturing rapidly evolving social trends. Existing topic models often struggle to accurately capture the underlying semantic patterns of short…

It has been shown that many generative models inherit and amplify societal biases. To date, there is no uniform/systematic agreed standard to control/adjust for these biases. This study examines the presence and manipulation of societal…

Text simplification (TS) systems rewrite text to make it more readable while preserving its content. However, what makes a text easy to read depends on the intended readers. Recent work has shown that pre-trained language models can…