相关论文: Tracing Relational Knowledge Recall in Large Langu…

Large Language Models (LLMs) are commonly criticized for not understanding language. However, many critiques focus on cognitive abilities that, in humans, are distinct from language processing. Here, we instead study a kind of understanding…

Large Vision-Language Models (LVLMs) answer visual questions by transferring information from images to text through a series of attention heads. While this image-to-text information flow is central to visual question answering, its…

Recent work exploring the capabilities of pre-trained large language models (LLMs) has demonstrated their ability to act as general pattern machines by completing complex token sequences representing a wide array of tasks, including…

Large language models (LLMs) demonstrate an impressive ability to utilise information within the context of their input sequences to appropriately respond to data unseen by the LLM during its training procedure. This ability is known as…

Large language models often reason beyond surface tokens, but the internal stage at which token-level information becomes abstract relational structure remains unclear. We investigate this question by analyzing how attention heads and…

We study whether Large Language Models (LLMs) inherently capture domain-specific nuances in natural language. Our experiments probe the domain sensitivity of LLMs by examining their ability to distinguish queries from different domains…

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular,…

Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts remains…

Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas. In this study, we examine how assigning a persona influences a model's reasoning on an objective task. Using activation patching, we take a first step…

We analyze how large language models (LLMs) represent out-of-context words, investigating their reliance on the given context to capture their semantics. Our likelihood-guided text perturbations reveal a correlation between token likelihood…

Recent years have witnessed a surge of research on leveraging large language models (LLMs) for sequential recommendation. LLMs have demonstrated remarkable potential in inferring users' nuanced preferences through fine-grained semantic…

We introduce the framework of "social learning" in the context of large language models (LLMs), whereby models share knowledge with each other in a privacy-aware manner using natural language. We present and evaluate two approaches for…

Large language models encapsulate knowledge and have demonstrated superior performance on various natural language processing tasks. Recent studies have localized this knowledge to specific model parameters, such as the MLP weights in…

Attributes of words and relations between two words are central to numerous tasks in Artificial Intelligence such as knowledge representation, similarity measurement, and analogy detection. Often when two words share one or more attributes…

Large Language Models (LLMs) are often evaluated against ideals of perfect Bayesian inference, yet growing evidence suggests that their in-context reasoning exhibits systematic forgetting of past information. Rather than viewing this…

Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various tasks but remain as black-box systems. Understanding the reasoning bottlenecks of LLMs has become a critical challenge, as these limitations are deeply tied…

Causal language models acquire vast amount of knowledge from general text corpus during pretraining, but the efficiency of knowledge learning is known to be unsatisfactory, especially when learning from knowledge-dense and small-sized…

Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful LLMs are and what factors influence LLMs' context…

Large Language Models (LLMs) have demonstrated strong performance in handling complex tasks requiring both extensive knowledge and reasoning abilities. However, the existing LLM inference pipeline operates as an opaque process without…

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…