Related papers: Linear representations in language models can chan…

The capabilities of large language models (LLMs) have sparked debate over whether such systems just learn an enormous collection of superficial statistics or a set of more coherent and grounded representations that reflect the real world.…

As large language models (LLMs) move from static reasoning tasks toward dynamic environments, their success depends on the ability to navigate and respond to an environment that changes as they interact at inference time. An underexplored…

High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in different paradigms of machine learning and data mining. These representations have different degrees of…

Language understanding research is held back by a failure to relate language to the physical world it describes and to the social interactions it facilitates. Despite the incredible effectiveness of language processing models to tackle…

Linear approximations to the decision boundary of a complex model have become one of the most popular tools for interpreting predictions. In this paper, we study such linear explanations produced either post-hoc by a few recent methods or…

Methods and insights from statistical physics are finding an increasing variety of applications where one seeks to understand the emergent properties of a complex interacting system. One such area concerns the dynamics of language at a…

Conversational participants tend to immediately and unconsciously adapt to each other's language styles: a speaker will even adjust the number of articles and other function words in their next utterance in response to the number in their…

Associative learning--forming links between co-occurring items--is fundamental to human cognition, reshaping internal representations in complex ways. Testing hypotheses on how representational changes occur in biological systems is…

The nouns of our language refer to either concrete entities (like a table) or abstract concepts (like justice or love), and cognitive psychology has established that concreteness influences how words are processed. Accordingly,…

Translations capture important information about languages that can be used as implicit supervision in learning linguistic properties and semantic representations. In an information-centric view, translated texts may be considered as…

While large language models (LLMs) are generally considered proficient in generating language, how similar their language usage is to that of humans remains understudied. In this paper, we test whether models exhibit linguistic convergence,…

Pragmatics and non-literal language understanding are essential to human communication, and present a long-standing challenge for artificial language models. We perform a fine-grained comparison of language models and humans on seven…

When we view visualizations, we not only have a visual representation of the data, but also a verbal one. Recent work has shown that these visual representations of data can be biased, such that the position of a line in a chart will be…

Large Language Models (LLMs) are widely used as conversational agents, exploiting their capabilities in various sectors such as education, law, medicine, and more. However, LLMs are often subjected to context-shifting behaviour, resulting…

The development of highly fluent large language models (LLMs) has prompted increased interest in assessing their reasoning and problem-solving capabilities. We investigate whether several LLMs can solve a classic type of deductive reasoning…

We present an analysis of user conversations in on-line social media and their evolution over time. We propose a dynamic model that accurately predicts the growth dynamics and structural properties of conversation threads. The model…

Language understanding (LU) and dialogue policy learning are two essential components in conversational systems. Human-human dialogues are not well-controlled and often random and unpredictable due to their own goals and speaking habits.…

Figurative language is ubiquitous in English. Yet, the vast majority of NLP research focuses on literal language. Existing text representations by design rely on compositionality, while figurative language is often non-compositional. In…

Following the recent success of word embeddings, it has been argued that there is no such thing as an ideal representation for words, as different models tend to capture divergent and often mutually incompatible aspects like…

We present a visually grounded model of speech perception which projects spoken utterances and images to a joint semantic space. We use a multi-layer recurrent highway network to model the temporal nature of spoken speech, and show that it…