相关论文: Improving Causal Interventions in Amnesic Probing …

Estimating mutual information from text usually requires training a task-specific critic, which limits its use in low-data settings. We ask whether large language models can instead estimate pointwise mutual information zero-shot, using…

Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little…

Self-supervised objectives have driven major advances in NLP by leveraging large-scale unlabeled data, but such resources are scarce for many of the world's languages. Surprisingly, they have not been explored much for character-level…

Natural language processing models tend to learn and encode social biases present in the data. One popular approach for addressing such biases is to eliminate encoded information from the model's representations. However, current methods…

Recently, Provenance-based Intrusion Detection Systems (PIDSes) have been widely used for endpoint threat analysis. These studies can be broadly categorized into rule-based detection systems and learning-based detection systems. Among…

Reinforcement Learning (RL) has become a key approach for enhancing the reasoning capabilities of large language models. However, prevalent RL approaches like proximal policy optimization and group relative policy optimization suffer from…

Language models can behave in unexpected and unsafe ways, and so it is valuable to monitor their outputs. Internal activations of language models encode additional information that could be useful for this. The baseline approach for…

Most modern NLP systems make use of pre-trained contextual representations that attain astonishingly high performance on a variety of tasks. Such high performance should not be possible unless some form of linguistic structure inheres in…

Image memorability, i.e., how likely an image is to be remembered, has traditionally been studied in computer vision either as a passive prediction task, with models regressing a scalar score, or with generative methods altering the visual…

Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performance on knowledge that…

User specifications or legal frameworks often require information to be removed from pretrained models, including large language models (LLMs). This requires deleting or "forgetting" a set of data points from an already-trained model, which…

Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely…

This position paper investigates the potential of integrating insights from language impairment research and its clinical treatment to develop human-inspired learning strategies and evaluation frameworks for language models (LMs). We…

Hallucination in large language models (LLMs) remains a critical barrier to their safe deployment. For hallucination detection to be practical in real-world scenarios, the use of efficient small models is essential to ensure low latency and…

Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…

Modern neural networks often encode unwanted concepts alongside task-relevant information, leading to fairness and interpretability concerns. Existing post-hoc approaches can remove undesired concepts but often degrade useful signals. We…

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between two views of an image. NCE uses randomly sampled negative…

Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning research community has increasingly turned toward empirical…

Language Model (LM) pruning compresses the model by removing weights, nodes, or other parts of its architecture. Typically, pruning focuses on the resulting efficiency gains at the cost of effectiveness. However, when looking at how…