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

Existing multilingual embedding models often encounter challenges in cross-lingual scenarios due to imbalanced linguistic resources and less consideration of cross-lingual alignment during training. Although standardized contrastive…

Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…

With the emergence of automatic speech recognition (ASR) models, converting the spoken form text (from ASR) to the written form is in urgent need. This inverse text normalization (ITN) problem attracts the attention of researchers from…

Language identification (LID) is a fundamental step in curating multilingual corpora. However, LID models still perform poorly for many languages, especially on the noisy and heterogeneous web data often used to train multilingual language…

Extracting patient information from unstructured text is a critical task in health decision-support and clinical research. Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context…

We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR). Compared with the original textual input, AMR is a structured semantic representation that presents the core concepts…

While mechanistic interpretability has developed powerful tools to analyze the internal workings of Large Language Models (LLMs), their complexity has created an accessibility gap, limiting their use to specialists. We address this…

Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks. There are two main paradigms for learning such representations: (1) alignment, which maps different independently…

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Named entity recognition (NER) is a fundamental component in many applications, such as Web Search and Voice Assistants. Although deep neural networks greatly improve the performance of NER, due to the requirement of large amounts of…

Multilingual LLMs often have knowledge disparities across languages, with larger gaps in under-resourced languages. Teaching LLMs to abstain in the face of knowledge gaps is thus a promising strategy to mitigate hallucinations in…

Dense retrieval in multilingual settings often searches over mixed-language collections, yet multilingual embeddings encode language identity alongside semantics. This language signal can inflate similarity for same-language pairs and crowd…

This paper addresses spoken language identification (SLI) and speech recognition of multilingual broadcast and institutional speech, real application scenarios that have been rarely addressed in the SLI literature. Observing that in these…

Negation and uncertainty modeling are long-standing tasks in natural language processing. Linguistic theory postulates that expressions of negation and uncertainty are semantically independent from each other and the content they modify.…

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Entity linking (EL) is the task of disambiguating mentions in text by associating them with entries in a predefined database of mentions (persons, organizations, etc). Most previous EL research has focused mainly on one language, English,…

AI researchers and practitioners increasingly apply large language models (LLMs) to what we call reasoning-intensive regression (RiR), i.e., deducing subtle numerical scores from text. Unlike standard language regression tasks such as…

Pseudo-labeling has recently shown promise in end-to-end automatic speech recognition (ASR). We study Iterative Pseudo-Labeling (IPL), a semi-supervised algorithm which efficiently performs multiple iterations of pseudo-labeling on…

Cross-lingual information extraction (CLIE) is an important and challenging task, especially in low resource scenarios. To tackle this challenge, we propose a training method, called Halo, which enforces the local region of each hidden…

We expose a critical limitation in current approaches to machine unlearning in language models: despite the apparent success of unlearning algorithms, information about the forgotten data remains linearly decodable from internal…