Related papers: A Simple and Effective Method To Eliminate the Sel…

The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models. We present Iterative Null-space Projection (INLP), a novel…

Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigating…

Fine-tuning pretrained language models (LMs) without making any architectural changes has become a norm for learning various language downstream tasks. However, for non-language downstream tasks, a common practice is to employ task-specific…

Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Self-supervised learning (SSL) has reduced the reliance on expensive labeling in speech technologies by learning meaningful representations from unannotated data. Since most SSL-based downstream tasks prioritize content information in…

Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms…

Integrating logical reasoning and machine learning by approximating logical inference with differentiable operators is a widely used technique in Neuro-Symbolic systems. However, some differentiable operators could bring a significant bias…

BERT and other large-scale language models (LMs) contain gender and racial bias. They also exhibit other dimensions of social bias, most of which have not been studied in depth, and some of which vary depending on the language. In this…

Collaborative research often includes contributors with varied perspectives from diverse linguistic backgrounds. However, English as a Second Language (ESL) researchers often struggle to communicate during meetings in English and comprehend…

Although the multilingual capability of LLMs offers new opportunities to overcome the language barrier, do these capabilities translate into real-life scenarios where linguistic divide and knowledge conflicts between multilingual sources…

We introduce an Item Response Theory (IRT)-based framework to detect and quantify socioeconomic bias in large language models (LLMs) without relying on subjective human judgments. Unlike traditional methods, IRT accounts for item…

Drawing real world social inferences usually requires taking into account information from multiple modalities. Language is a particularly powerful source of information in social settings, especially in novel situations where language can…

Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are…

Vision-and-Language Navigation (VLN) tasks require an agent to navigate through the environment based on language instructions. In this paper, we aim to solve two key challenges in this task: utilizing multilingual instructions for improved…

Visual Information Extraction (VIE) plays a crucial role in the comprehension of semi-structured documents, and several pre-trained models have been developed to enhance performance. However, most of these works are monolingual (usually…

Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite…

While multilingual large language models generally perform adequately, and sometimes even rival English performance on high-resource languages (HRLs), they often significantly underperform on low-resource languages (LRLs). Among several…

Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantly rely on language…

Both masked image modeling (MIM) and natural language supervision have facilitated the progress of transferable visual pre-training. In this work, we seek the synergy between two paradigms and study the emerging properties when MIM meets…