6 accepted papers
Large Language Models (LLMs) are powerful in-context learners, achieving strong performance with just a few high-quality demonstrations. However, fairness concerns arise in many in-context classification tasks, especially when predictions involve sensitive attributes. To address this, we propose JUD…
Multi-modal retrieval-augmented Question Answering (MRAQA), integrating text and images, has gained significant attention in information retrieval (IR) and natural language processing (NLP). Traditional ranking methods rely on small encoder-based language models, which are incompatible with modern d…
Building an NLP training set for understudied languages, including Indigenous and endangered languages, often faces challenges due to varying degrees of resource limitations in the speaker communities. What are some reasonable approaches for training set construction in these cases? We address this
In recent research, contrastive learning has proven to be a highly effective method for representation learning and is widely used for dense retrieval. However, we identify that relying solely on contrastive learning can lead to suboptimal retrieval performance. On the other hand, despite many retri…
The product attribute value extraction (AVE) task aims to capture key factual information from product profiles, and is useful for several downstream applications in e-Commerce platforms. Previous contributions usually formulate this task using sequence labeling or reading comprehension architecture…
Automatic extraction of product attribute values is an important enabling technology in e-Commerce platforms. This task is usually modeled using sequence labeling architectures, with several extensions to handle multi-attribute extraction. One line of previous work constructs attribute-specific mode…