相关论文: Semantic Structure of Feature Space in Large Langu…

Sound symbolism is a linguistic concept that refers to non-arbitrary associations between phonetic forms and their meanings. We suggest that this can be a compelling probe into how Multimodal Large Language Models (MLLMs) interpret auditory…

We study feature interactions in the context of feature attribution methods for post-hoc interpretability. In interpretability research, getting to grips with feature interactions is increasingly recognised as an important challenge,…

Large language models (LLMs) are the foundation of the current successes of artificial intelligence (AI), however, they are unavoidably biased. To effectively communicate the risks and encourage mitigation efforts these models need adequate…

Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, natural language feature descriptions can be vague, inconsistent, and require manual relabeling. In response,…

Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of…

Human language has a distinct systematic structure, where utterances break into individually meaningful words which are combined to form phrases. We show that natural-language-like systematicity arises in codes that are constrained by a…

Spatial relations are a basic part of human cognition. However, they are expressed in natural language in a variety of ways, and previous work has suggested that current vision-and-language models (VLMs) struggle to capture relational…

This thesis investigates how the sub-structure of words can be accounted for in probabilistic models of language. Such models play an important role in natural language processing tasks such as translation or speech recognition, but often…

Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of common sense reasoning ability. We show, however, with a new diagnostic…

We introduce a new approach to systematically map features discovered by sparse autoencoder across consecutive layers of large language models, extending earlier work that examined inter-layer feature links. By using a data-free cosine…

The concept of beauty has been debated by philosophers and psychologists for centuries, but most definitions are subjective and metaphysical, and deficit in accuracy, generality, and scalability. In this paper, we present a novel study on…

Human-like personality traits have recently been discovered in large language models, raising the hypothesis that their (known and as yet undiscovered) biases conform with human latent psychological constructs. While large conversational…

Word embeddings are a popular way to improve downstream performances in contemporary language modeling. However, the underlying geometric structure of the embedding space is not well understood. We present a series of explorations using…

Humans can effortlessly describe what they see, yet establishing a shared representational format between vision and language remains a significant challenge. Emerging evidence suggests that human brain representations in both vision and…

Representing words by vectors, or embeddings, enables computational reasoning and is foundational to automating natural language tasks. For example, if word embeddings of similar words contain similar values, word similarity can be readily…

Large language models follow a lineage of many NLP applications that were directly inspired by distributional semantics, but do not seem to be closely related to it anymore. In this paper, we propose to employ the distributional theory of…

Large language models encode knowledge in various domains and demonstrate the ability to understand visualizations. They may also capture visualization design knowledge and potentially help reduce the cost of formative studies. However, it…

The contribution of this paper is to provide a semantic model (using soft constraints) of the words used by web-users to describe objects in a language game; a game in which one user describes a selected object of those composing the scene,…

Lexical iconicity, a direct relation between a word's meaning and its form, is an important aspect of every natural language, most commonly manifesting through sound-meaning associations. Since Large language models' (LLMs') access to both…

Styles of typefaces or fonts are often associated with specific impressions, such as heavy, contemporary, or elegant. This indicates that there are certain correlations between font shapes and their impressions. To understand the…