Related papers: Number Representations in LLMs: A Computational Pa…
Analogical reasoning is at the core of human cognition, serving as an important foundation for a variety of intellectual activities. While prior work has shown that LLMs can represent task patterns and surface-level concepts, it remains…
Large language models (LLMs) excel at modeling relationships between strings in natural language and have shown promise in extending to other symbolic domains like coding or mathematics. However, the extent to which they implicitly model…
The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…
Understanding internal representations of neural models is a core interest of mechanistic interpretability. Due to its large dimensionality, the representation space can encode various aspects about inputs. To what extent are different…
Large Language Models (LLMs) have recently been successfully applied to regression tasks -- such as time series forecasting and tabular prediction -- by leveraging their in-context learning abilities. However, their autoregressive decoding…
From extracting features to generating text, the outputs of large language models (LLMs) typically rely on the final layers, following the conventional wisdom that earlier layers capture only low-level cues. However, our analysis shows that…
Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped Transformers (LTs)--architectures that increase computational…
Large Vision Language Models (LVLMs) exhibit strong visual understanding and reasoning abilities. However, whether their internal representations reflect human visual cognition is still under-explored. In this paper, we address this by…
Large language models (LLMs) are the result of a massive experiment in bottom-up, data-driven reverse engineering of language at scale. Despite their utility in a number of downstream NLP tasks, ample research has shown that LLMs are…
The linear representation hypothesis is the informal idea that semantic concepts are encoded as linear directions in the representation spaces of large language models (LLMs). Previous work has shown how to make this notion precise for…
Large Language Models (LLMs) are increasingly expected to navigate the nuances of human emotion. While research confirms that LLMs can simulate emotional intelligence, their internal emotional mechanisms remain largely unexplored. This…
Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting…
Large language models (LLMs) show remarkable capabilities across a variety of tasks. Despite the models only seeing text in training, several recent studies suggest that LLM representations implicitly capture aspects of the underlying…
Large language models (LLMs) achieve impressive results over various tasks, and ever-expanding public repositories contain an abundance of pre-trained models. Therefore, identifying the best-performing LLM for a given task is a significant…
Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In…
Large Language Models (LLMs) have demonstrated remarkable abilities in text comprehension and logical reasoning, indicating that the text representations learned by LLMs can facilitate their language processing capabilities. In…
Large language models (LLMs) demonstrate extraordinary abilities in a wide range of natural language processing (NLP) tasks. In this paper, we show that, beyond text understanding capability, LLMs are capable of processing text layouts that…
Large language models (LLMs) have shown remarkable success in language modelling due to scaling laws found in model size and the hidden dimension of the model's text representation. Yet, we demonstrate that compressed representations of…
Neural network models of language have long been used as a tool for developing hypotheses about conceptual representation in the mind and brain. For many years, such use involved extracting vector-space representations of words and using…
We study how large language models (LLMs) ``think'' through their representation space. We propose a novel geometric framework that models an LLM's reasoning as flows -- embedding trajectories evolving where logic goes. We disentangle…