相关论文: DSAI: Unbiased and Interpretable Latent Feature Ex…

Large language models (LLMs) demonstrate exceptional performance on tasks requiring complex linguistic abilities, such as reference disambiguation and metaphor recognition/generation. Although LLMs possess impressive capabilities, their…

In modern business processes, the amount of data collected has increased substantially in recent years. Because this data can potentially yield valuable insights, automated knowledge extraction based on process mining has been proposed,…

We study the challenge of achieving theoretically grounded feature recovery using Sparse Autoencoders (SAEs) for the interpretation of Large Language Models. Existing SAE training algorithms often lack rigorous mathematical guarantees and…

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable AI making strides in…

Recent advances in generative AI have led to remarkable interest in using systems that rely on large language models (LLMs) for practical applications. However, meaningful evaluation of these systems in real-world scenarios comes with a…

The success of deep networks is crucially attributed to their ability to capture latent features within a representation space. In this work, we investigate whether the underlying learned features of a model can be efficiently retrieved…

Recent years have seen important advances in the building of interpretable models, machine learning models that are designed to be easily understood by humans. In this work, we show that large language models (LLMs) are remarkably good at…

Current methods for evaluating large language models (LLMs) typically focus on high-level tasks such as text generation, without targeting a particular AI application. This approach is not sufficient for evaluating LLMs for Responsible AI…

Aligning large language models (LLMs) typically aim to reflect general human values and behaviors, but they often fail to capture the unique characteristics and preferences of individual users. To address this gap, we introduce the concept…

Integration of artificial intelligence (AI) into life cycle assessment (LCA) has accelerated in recent years, with numerous studies successfully adapting machine learning algorithms to support various stages of LCA. Despite this rapid…

We introduce a new version of deep state-space models (DSSMs) that combines a recurrent neural network with a state-space framework to forecast time series data. The model estimates the observed series as functions of latent variables that…

This review synthesizes the nascent but critical field of developmental interpretability for Large Language Models. We chart the field's evolution from static, post-hoc analysis of trained models to a dynamic investigation of the training…

As machine learning models grow more complex and their applications become more high-stakes, tools for explaining model predictions have become increasingly important. This has spurred a flurry of research in model explainability and has…

Recently, Large Language Models (LLMs) have been applied to scientific equation discovery, leveraging their embedded scientific knowledge for hypothesis generation. However, current methods typically confine LLMs to the role of an equation…

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle…

This paper presents a comprehensive evaluation of the capabilities of Large Language Models (LLMs) in metaphor interpretation across multiple datasets, tasks, and prompt configurations. Although metaphor processing has gained significant…

While mechanistic interpretability tools like Sparse Autoencoders (SAEs) can uncover meaningful features within Large Language Models (LLMs), a critical gap remains in transforming these insights into practical actions for model…

Large Language Models (LLMs) are effective for data augmentation in classification tasks like intent detection. In some cases, they inadvertently produce examples that are ambiguous with regard to untargeted classes. We present DDAIR…

Deep learning (DL) has substantially enhanced natural language processing (NLP) in healthcare research. However, the increasing complexity of DL-based NLP necessitates transparent model interpretability, or at least explainability, for…