Related papers: Hyperpolyglot LLMs: Cross-Lingual Interpretability…

As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial. Despite the growing number of general embedding models, prior work often overlooks the critical role of training data…

Cross-lingual embeddings represent the meaning of words from different languages in the same vector space. Recent work has shown that it is possible to construct such representations by aligning independently learned monolingual embedding…

How related are the representations learned by neural language models, translation models, and language tagging tasks? We answer this question by adapting an encoder-decoder transfer learning method from computer vision to investigate the…

Multilingual Language Models (MLLMs) exhibit robust cross-lingual transfer capabilities, or the ability to leverage information acquired in a source language and apply it to a target language. These capabilities find practical applications…

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs…

Autoregressive vision-language models (VLMs) can handle many tasks within a single model, yet the representations that enable this capability remain opaque. We find that VLMs align conceptually equivalent inputs into a shared task vector,…

Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages. In this paper, we extend these probing methods to a multilingual context, investigating the…

Large language models (LLMs) can spell out tokens character by character with high accuracy, yet they struggle with more complex character-level tasks, such as identifying compositional subcomponents within tokens. In this work, we…

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…

Multilingual pre-trained models exhibit zero-shot cross-lingual transfer, where a model fine-tuned on a source language achieves surprisingly good performance on a target language. While studies have attempted to understand transfer, they…

Recent studies have demonstrated the overwhelming advantage of cross-lingual pre-trained models (PTMs), such as multilingual BERT and XLM, on cross-lingual NLP tasks. However, existing approaches essentially capture the co-occurrence among…

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

With hundreds of thousands of language models available on Huggingface today, efficiently evaluating and utilizing these models across various downstream, tasks has become increasingly critical. Many existing methods repeatedly learn…

Recommendation systems, for documents, have become tools to find relevant content on the Web. However, these systems have limitations when it comes to recommending documents in languages different from the query language, which means they…

Multilingual Large Language Models (LLMs) have gained large popularity among Natural Language Processing (NLP) researchers and practitioners. These models, trained on huge datasets, show proficiency across various languages and demonstrate…

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this…

Large language models (LLMs) reliably predict neural activity during language comprehension and transformer depth has been interpreted as mirroring hierarchical cortical organization. However, it remains unclear whether such alignment…

The advancement of Multimodal Large Language Models (MLLMs) has greatly accelerated the development of applications in understanding integrated texts and images. Recent works leverage image-caption datasets to train MLLMs, achieving…

Large language models (LLMs) represent words through contextual word embeddings encoding different language properties like semantics and syntax. Understanding these properties is crucial, especially for researchers investigating language…

Subword tokenizers trained on multilingual corpora naturally produce overlapping tokens across languages. Does token overlap facilitate cross-lingual transfer or instead introduce interference between languages? Prior work offers mixed…