相关论文: From Narrow Unlearning to Emergent Misalignment: C…

Recent unlearning methods for LLMs are vulnerable to relearning attacks: knowledge believed-to-be-unlearned re-emerges by fine-tuning on a small set of (even seemingly-unrelated) examples. We study this phenomenon in a controlled setting…

We study the minimal error of the Empirical Risk Minimization (ERM) procedure in the task of regression, both in the random and the fixed design settings. Our sharp lower bounds shed light on the possibility (or impossibility) of adapting…

Fine-tuning aligned language models on benign tasks unpredictably degrades safety guardrails, even when training data contains no harmful content and developers have no adversarial intent. We show that the prevailing explanation, that…

Detecting and handling misspecified objectives, such as reward functions, has been widely recognized as one of the central challenges within the domain of Artificial Intelligence (AI) safety research. However, even with the recognition of…

Conformal unlearning aims to ensure that a trained conformal predictor miscovers data points with specific shared characteristics, such as those from a particular label class, associated with a specific user, or belonging to a defined…

Misinformation is prevalent in various fields such as education, politics, health, etc., causing significant harm to society. However, current methods for cross-domain misinformation detection rely on effort- and resource-intensive…

As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern. While fine-tuning models on domain-specific datasets is often employed to improve model performance, it can…

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

Adversarial attacks for machine learning models have become a highly studied topic both in academia and industry. These attacks, along with traditional security threats, can compromise confidentiality, integrity, and availability of…

Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove specific content…

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In…

An extreme learning machine (ELM) can be regarded as a two stage feed-forward neural network (FNN) learning system which randomly assigns the connections with and within hidden neurons in the first stage and tunes the connections with…

Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…

Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing serious privacy risks. To mitigate this, MLLM unlearning methods are proposed, which fine-tune MLLMs to reduce…

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic "I don't know'', failing to distinguish input-level ambiguity (data uncertainty) from capability…

Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled. This paper introduces a new method to identify such samples and mitigate their impact when training neural…

Entity Matching (EM)--the task of determining whether two data records refer to the same real-world entity--is a core task in data integration. Recent advances in deep learning have set a new standard for EM, particularly through…

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Accurate assessments of extreme weather events are vital for research and policy, yet localized and granular data remain scarce in many parts of the world. This data gap limits our ability to analyze potential outcomes and implications of…