Related papers: Gyan: An Explainable Neuro-Symbolic Language Model

Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based…

The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrect or nonsensical outputs. These errors can propagate…

This position paper argues that large language models (LLMs) can make cultural context, and therefore human meaning, legible at an unprecedented scale in AI-based sociotechnical systems. We argue that such systems have previously been…

Large language models have been shown to suffer from reasoning inconsistency issues. That is, they fail more in situations unfamiliar to the training data, even though exact or very similar reasoning paths exist in more common cases that…

Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks. Yet, the exact capabilities of these black-box models are still poorly…

Recent advances in methods focused on the grounding problem have resulted in techniques that can be used to construct a symbolic language associated with a specific domain. Inspired by how humans communicate complex ideas through language,…

What do large language models actually model? Do they tell us something about human capacities, or are they models of the corpus we've trained them on? I give a non-deflationary defence of the latter position. Cognitive science tells us…

Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented…

Generative AI systems have entered everyday academic, professional, and personal life with remarkable speed, yet most users encounter them as mysterious artifacts rather than intelligible systems. This chapter discusses large language…

Recent advancements in large language models have demonstrated that extended inference through techniques can markedly improve performance, yet these gains come with increased computational costs and the propagation of inherent biases found…

Large Pre-trained Transformers exhibit an intriguing capacity for in-context learning. Without gradient updates, these models can rapidly construct new predictors from demonstrations presented in the inputs. Recent works promote this…

Artificial Intelligence models are becoming increasingly more powerful and accurate, supporting or even replacing humans' decision making. But with increased power and accuracy also comes higher complexity, making it hard for users to…

LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for many tasks. The current established technology of LLMs is to process input and generate output at the token level. This is in sharp…

Generative pre-trained transformer (GPT) models have revolutionized the field of natural language processing (NLP) with remarkable performance in various tasks and also extend their power to multimodal domains. Despite their success, large…

Recent studies have adopted pre-trained language models, such as CodeT5 and CodeGPT, for automated program generation tasks like code generation, repair, and translation. Numerous language model-based approaches have been proposed and…

Recently, deep neural networks (DNNs) have achieved great success in semantically challenging NLP tasks, yet it remains unclear whether DNN models can capture compositional meanings, those aspects of meaning that have been long studied in…

In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between…

Although language models are trained to mimic humans, the resulting systems display capabilities beyond the scope of any one person. To understand this phenomenon, we use a controlled setting to identify properties of the training data that…

As machine learning models and autonomous agents are increasingly deployed in high-stakes, real-world domains such as healthcare, security, finance, and robotics, the need for transparent and trustworthy explanations has become critical. To…

Large, pretrained language models infer powerful representations that encode rich semantic and syntactic content, albeit implicitly. In this work we introduce a novel neural language model that enforces, via inductive biases, explicit…