Related papers: Simplicity Bias in Transformers and their Ability …

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks. The attention mechanism in the Transformer…

Neural architectures tend to fit their data with relatively simple functions. This "simplicity bias" is widely regarded as key to their success. This paper explores the limits of this principle. Building on recent findings that the…

Transformers exhibit compositional reasoning on sequences not observed during training, a capability often attributed to in-context learning (ICL) and skill composition. We investigate this phenomenon using the Random Hierarchy Model (RHM),…

Transformers struggle with length generalisation, displaying poor performance even on basic tasks. We test whether these limitations can be explained through two key failures of the self-attention mechanism. The first is the inability to…

Recent work has shown that the computations of Transformers can be simulated in the RASP family of programming languages. These findings have enabled improved understanding of the expressive capacity and generalization abilities of…

In the last few years, the ML community has created a number of new NLP models based on transformer architecture. These models have shown great performance for various NLP tasks on benchmark datasets, often surpassing SOTA results. Buoyed…

During the pre-training step of natural language models, the main objective is to learn a general representation of the pre-training dataset, usually requiring large amounts of textual data to capture the complexity and diversity of natural…

Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks,…

Learning algorithms become more powerful, often at the cost of increased complexity. In response, the demand for algorithms to be transparent is growing. In NLP tasks, attention distributions learned by attention-based deep learning models…

This paper investigates the ability of transformer-based models to learn structural recursion from examples. Recursion is a universal concept in both natural and formal languages. Structural recursion is central to the programming language…

A simple design recipe for deep Transformers is to compose identical building blocks. But standard transformer blocks are far from simple, interweaving attention and MLP sub-blocks with skip connections & normalisation layers in precise…

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

Finetuning on narrow domains has become an essential tool to adapt Large Language Models (LLMs) to specific tasks and to create models with known unusual properties that are useful for research. We show that narrow finetuning creates strong…

Large language models (LLM) have emerged as a powerful tool for AI, with the key ability of in-context learning (ICL), where they can perform well on unseen tasks based on a brief series of task examples without necessitating any…

Because language is creative, any reasonable language model must generalize, deciding what to say in novel contexts by using information from similar contexts. But what about contexts that are not novel but merely infrequent? In…

A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs). However, a number of redundant parameters which contribute less to the downstream task are observed in a directly fine-tuned model. We consider the…

A common method to study deep learning systems is to use simplified model representations--for example, using singular value decomposition to visualize the model's hidden states in a lower dimensional space. This approach assumes that the…

Sampling biases can cause distribution shifts between train and test datasets for supervised learning tasks, obscuring our ability to understand the generalization capacity of a model. This is especially important considering the wide…

A growing intuition in machine learning suggests a link between sparsity and interpretability. We introduce a novel self-ablation mechanism to investigate this connection ante-hoc in the context of language transformers. Our approach…

In-context learning (ICL) enables transformers to adapt to new tasks through contextual examples without parameter updates. While existing research has typically studied ICL in fixed-complexity environments, practical language models…