相关论文: Filtering Context Mitigates Scarcity and Selection…

The increasing digitization of political speech has opened the door to studying a new dimension of political behavior using text analysis. This work investigates the value of word-level statistical data from the US Congressional…

Deep Learning heavily depends on large labeled datasets which limits further improvements. While unlabeled data is available in large amounts, in particular in image recognition, it does not fulfill the closed world assumption of…

The emerging in-context learning (ICL) ability of large language models (LLMs) has prompted their use for predictive tasks in various domains with different data types, including tabular data, facilitated by serialization methods. However,…

Despite the surprising few-shot performance of in-context learning (ICL), it is still a common practice to randomly sample examples to serve as context. This paper advocates a new principle for ICL: self-adaptive in-context learning. The…

Vision-language co-embedding networks, such as CLIP, provide a latent embedding space with semantic information that is useful for downstream tasks. We hypothesize that the embedding space can be disentangled to separate the information on…

We present BiasLab, a dataset of 300 political news articles annotated for perceived ideological bias. These articles were selected from a curated 900-document pool covering diverse political events and source biases. Each article is…

Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of…

Understanding politics is challenging because the politics take the influence from everything. Even we limit ourselves to the political context in the legislative processes; we need a better understanding of latent factors, such as…

Feature disentanglement of the foreground target objects and the background surrounding context has not been yet fully accomplished. The lack of network interpretability prevents advancing for feature disentanglement and better…

Bias discovery is critical for black-box generative models, especiall text-to-image (TTI) models. Existing works predominantly focus on output-level demographic distributions, which do not necessarily guarantee concept representations to be…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

The amount of data for processing and categorization grows at an ever increasing rate. At the same time the demand for collaboration and transparency in organizations, government and businesses, drives the release of data from internal…

Prior work on ideology prediction has largely focused on single modalities, i.e., text or images. In this work, we introduce the task of multimodal ideology prediction, where a model predicts binary or five-point scale ideological leanings,…

After pre-training by generating the next word conditional on previous words, the Language Model (LM) acquires the ability of In-Context Learning (ICL) that can learn a new task conditional on the context of the given in-context examples…

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…

Machine learning systems are increasingly deployed in high-stakes domains, yet they remain vulnerable to bias systematic disparities that disproportionately impact specific demographic groups. Traditional bias detection methods often depend…

Off-policy evaluation can leverage logged data to estimate the effectiveness of new policies in e-commerce, search engines, media streaming services, or automatic diagnostic tools in healthcare. However, the performance of baseline…

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized examples relevant to a…

Recently we have presented the analytical relationship between choice probabilities, noise correlations and read-out weights in the classical feedforward decision-making framework (Haefner et al. 2013). The derivation assumed that…