Related papers: Bears, all bears, and some bears. Language Constra…

Large language models (LLMs) have complicated internal dynamics, but induce representations of words and phrases whose geometry we can study. Human language processing is also opaque, but neural response measurements can provide (noisy)…

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

Two major areas of interest in the era of Large Language Models regard questions of what do LLMs know, and if and how they may be able to reason (or rather, approximately reason). Since to date these lines of work progressed largely in…

We propose a segmental neural language model that combines the generalization power of neural networks with the ability to discover word-like units that are latent in unsegmented character sequences. In contrast to previous segmentation…

Transformer language models have received widespread public attention, yet their generated text is often surprising even to NLP researchers. In this survey, we discuss over 250 recent studies of English language model behavior before…

Natural language generation (NLG) tasks are often subject to inherent variability; e.g. predicting the next word given a context has multiple valid responses, evident when asking multiple humans to complete the task. While having language…

Steering vectors (SVs) have been proposed as an effective approach to adjust language model behaviour at inference time by intervening on intermediate model activations. They have shown promise in terms of improving both capabilities and…

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Human language acquisition is an efficient, supervised, and continual process. In this work, we took inspiration from how human babies acquire their first language, and developed a computational process for word acquisition through…

How do learners acquire languages from the limited data available to them? This process must involve some inductive biases - factors that affect how a learner generalizes - but it is unclear which inductive biases can explain observed…

Idiomatic expressions are an integral part of human languages, often used to express complex ideas in compressed or conventional ways (e.g. eager beaver as a keen and enthusiastic person). However, their interpretations may not be…

Given the broad capabilities of large language models, it should be possible to work towards a general-purpose, text-based assistant that is aligned with human values, meaning that it is helpful, honest, and harmless. As an initial foray in…

Can models generalize attribute knowledge across semantically and perceptually dissimilar categories? While prior work has addressed attribute prediction within narrow taxonomic or visually similar domains, it remains unclear whether…

One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the…

Natural language often contains ambiguities that can lead to misinterpretation and miscommunication. While humans can handle ambiguities effectively by asking clarifying questions and/or relying on contextual cues and common-sense…

Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure…

Adults vary greatly in how effectively they learn a new language, but the signals driving the learning processes and individual differences remain unclear. Over seven days, we tracked behavioral learning and collected fMRI data from 102…

Certain concepts, words, and images are intuitively more similar than others (dog vs. cat, dog vs. spoon), though quantifying such similarity is notoriously difficult. Indeed, this kind of computation is likely a critical part of learning…

Although virtual agents are increasingly situated in environments where natural language is the most effective mode of interaction with humans, these exchanges are rarely used as an opportunity for learning. Leveraging language interactions…

Large-scale pretrained language models (LMs) are said to ``lack the ability to connect utterances to the world'' (Bender and Koller, 2020), because they do not have ``mental models of the world' '(Mitchell and Krakauer, 2023). If so, one…