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

We propose CHRT (Control Hidden Representation Transformation) - a controlled language generation framework that steers large language models to generate text pertaining to certain attributes (such as toxicity). CHRT gains attribute control…

With the introduction of ChatGPT, OpenAI made large language models (LLM) accessible to users with limited IT expertise. However, users with no background in natural language processing (NLP) might lack a proper understanding of LLMs. Thus…

Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development…

Text-to-Image (TTI) models are powerful creative tools but risk amplifying harmful social biases. We frame representational societal bias assessment as an image curation and evaluation task and introduce a pilot benchmark of occupational…

During the pre-training step of natural language models, the main objective is to learn a general representation of the pre-training dataset, usually requiring large amounts of textual data to capture the complexity and diversity of natural…

This chapter examines the role of Machine Translation in perpetuating gender bias, highlighting the challenges posed by cross-linguistic settings and statistical dependencies. A comprehensive overview of relevant existing work related to…

Large language models trained on a mixture of NLP tasks that are converted into a text-to-text format using prompts, can generalize into novel forms of language and handle novel tasks. A large body of work within prompt engineering attempts…

In recent years, prompting has quickly become one of the standard ways of steering the outputs of generative machine learning models, due to its intuitive use of natural language. In this work, we propose a system conditioned on embeddings…

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

The rise of large language models (LLMs) has revolutionized natural language processing (NLP), yet the influence of prompt sentiment, a latent affective characteristic of input text, remains underexplored. This study systematically examines…

As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize on bias…

Text-to-image generation models have recently achieved astonishing results in image quality, flexibility, and text alignment, and are consequently employed in a fast-growing number of applications. Through improvements in multilingual…

Instruction-tuned large language models (LLMs), such as ChatGPT, have led to promising zero-shot performance in discriminative natural language understanding (NLU) tasks. This involves querying the LLM using a prompt containing the…

Prediction head is a crucial component of Transformer language models. Despite its direct impact on prediction, this component has often been overlooked in analyzing Transformers. In this study, we investigate the inner workings of the…

Text-to-image (T2I) generative models have gained increased popularity in the public domain. While boasting impressive user-guided generative abilities, their black-box nature exposes users to intentionally- and intrinsically-biased…

Prompt-based fine-tuning has become an essential method for eliciting information encoded in pre-trained language models for a variety of tasks, including text classification. For multi-class classification tasks, prompt-based fine-tuning…

Scientific articles play a crucial role in advancing knowledge and informing research directions. One key aspect of evaluating scientific articles is the analysis of citations, which provides insights into the impact and reception of the…

ChatGPT has the ability to generate grammatically flawless and seemingly-human replies to different types of questions from various domains. The number of its users and of its applications is growing at an unprecedented rate. Unfortunately,…

Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. However, the likelihood, a measure of LLM's plausibility for a sentence, can vary due to superficial differences in sentences,…

The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural…