相关论文: Evaluating Cross-Lingual Unlearning in Multilingua…

Large language models (LLMs) still struggle across tasks outside of high-resource languages. In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce. Building on prior…

We assess how multilingual language models maintain a shared multilingual representation space while still encoding language-sensitive information in each language. Using XLM-R as a case study, we show that languages occupy similar linear…

Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…

Vision-language models (VLMs) may memorize undesirable information from training data, motivating growing interest in machine unlearning. In this work, we present the first systematic survey and robustness analysis of VLM unlearning. We…

Multilingual pre-trained language models (MPLMs) not only can handle tasks in different languages but also exhibit surprising zero-shot cross-lingual transferability. However, MPLMs usually are not able to achieve comparable supervised…

As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention. Machine unlearning is introduced to seek to mitigate these risks by removing the influence of undesirable data.…

Recent advances in training multilingual language models on large datasets seem to have shown promising results in knowledge transfer across languages and achieve high performance on downstream tasks. However, we question to what extent the…

Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important -- especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept…

This survey examines multilingual vision-language models that process text and images across languages. We review 33 models and 23 benchmarks, spanning encoder-only and generative architectures, and identify a key tension between language…

In many multilingual text classification problems, the documents in different languages often share the same set of categories. To reduce the labeling cost of training a classification model for each individual language, it is important to…

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While…

Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting…

Machine unlearning empowers individuals with the `right to be forgotten' by removing their private or sensitive information encoded in machine learning models. However, it remains uncertain whether MU can be effectively applied to…

Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-linguistic reasoning abilities. This dual limitation makes it…

Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged as an efficient alternative to full retraining, aiming to…

The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on…

As global demand for multilingual large language models (LLMs) grows, most LLMs still remain overly focused on English, leading to the limited access to advanced AI for non-English speakers. Current methods to enhance multilingual…

Large language models memorize sensitive data from their pretraining corpora. In this work, we propose CE-U (Cross Entropy Unlearning), a loss function for unlearning. CE-U addresses fundamental limitations of gradient ascent approaches…

Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during…

Large Language Models (LLMs) store and retrieve vast amounts of factual knowledge acquired during pre-training. Prior research has localized and identified mechanisms behind knowledge recall; however, it has only focused on English…