相关论文: FAME: Fictional Actors for Multilingual Erasure

Large Language Models (LLMs) have shown remarkable capabilities, not only in generating human-like text, but also in acquiring knowledge. This highlights the need to go beyond the typical Natural Language Processing downstream benchmarks…

Large language models (LLMs) risk retaining sensitive, copyrighted, or harmful information from their training data. Entity-level unlearning addresses this issue by removing all knowledge of a specific entity while preserving the model's…

Large Language Models (LLMs) have emerged as personalized assistants for users across a wide range of tasks -- from offering writing support to delivering tailored recommendations or consultations. Over time, the interaction history between…

We attack the problem of learning face models for public faces from weakly-labelled images collected from web through querying a name. The data is very noisy even after face detection, with several irrelevant faces corresponding to other…

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…

Large language models (LLMs) in research and development toolchains produce output that triggers attribution of agency and understanding -- a cognitive illusion that degrades verification behavior and trust calibration. No existing…

Large language models (LLMs) are revolutionizing education, with LLM-based agents playing a key role in simulating student behavior. A major challenge in student simulation is modeling the diverse learning patterns of students at various…

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…

Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during pretraining. This paper addresses the challenge of modifying…

Large language models (LLMs) risk retaining unauthorized or sensitive information from their training data, which raises privacy concerns. LLM unlearning seeks to mitigate these risks by selectively removing specified data while maintaining…

The security of biomedical Multimodal Large Language Models (MLLMs) has attracted increasing attention. However, training samples easily contain private information and incorrect knowledge that are difficult to detect, potentially leading…

Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…

In this work, we assess the ability of foundation models to recall encyclopedic knowledge across a wide range of linguistic contexts. To support this, we: 1) produce a 20-language dataset that contains 303k factual associations paired with…

Large Language Models (LLMs) have demonstrated significant performance improvements across various cognitive tasks. An emerging application is using LLMs to enhance retrieval-augmented generation (RAG) capabilities. These systems require…

Large language models (LLMs) have shown remarkable performance on a variety of NLP tasks, and are being rapidly adopted in a wide range of use cases. It is therefore of vital importance to holistically evaluate the factuality of their…

Machine unlearning removes certain training data points and their influence from AI models (e.g., when a data owner revokes their consent to allow models to learn from the data). In this position paper, we propose to lift data-tracing…

We present the first comprehensive evaluation of cross-lingual unlearning in multilingual LLMs. Using translated TOFU benchmarks in seven language/script variants, we test major unlearning algorithms and show that most fail to remove facts…

Understanding how data moves, transforms, and persists, known as data flow, is fundamental to reasoning in procedural tasks. Despite their fluency in natural and programming languages, large language models (LLMs), although increasingly…

Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy concerns, especially…

Analogy is one of the core capacities of human cognition; when faced with new situations, we often transfer prior experience from other domains. Most work on computational analogy relies heavily on complex, manually crafted input. In this…