Related papers: A Comparative Investigation of Compositional Synta…
Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and…
Large language models (LLMs) are capable of solving a wide range of tasks, yet they have struggled with reasoning. To address this, we propose $\textbf{Additional Logic Training (ALT)}$, which aims to enhance LLMs' reasoning capabilities by…
Type "a sea otter with a pearl earring by Johannes Vermeer" or "a photo of a teddy bear on a skateboard in Times Square" into OpenAI's DALL-E-2 paint-by-text synthesis engine and you will not be disappointed by the delightful and eerily…
Traditional evaluations of reasoning capabilities of language models are dominated by adult-centric benchmarks that presuppose broad world knowledge, complex instruction following, and mature pragmatic competence. These assumptions are…
Is analogical reasoning a task that must be learned to solve from scratch by applying deep learning models to massive numbers of reasoning problems? Or are analogies solved by computing similarities between structured representations of…
Recent work has shown that despite their impressive capabilities, text-to-image diffusion models such as DALL-E 2 (Ramesh et al., 2022) can display strange behaviours when a prompt contains a word with multiple possible meanings, often…
This paper explores how natural-language descriptions of formal languages can be compared to their formal representations and how semantic differences can be explained. This is motivated from educational scenarios where learners describe a…
We provide a new multi-task benchmark for evaluating text-to-image models. We perform a human evaluation comparing the most common open-source (Stable Diffusion) and commercial (DALL-E 2) models. Twenty computer science AI graduate students…
Western music is largely governed by tonality, a quasi syntactic system regulating musical continuity and closure. Converging measures have established the psychological reality of tonality as a cognitive schema raising distinct expectancy…
We evaluate two large language models (LLMs) ability to perform argumentative reasoning. We experiment with argument mining (AM) and argument pair extraction (APE), and evaluate the LLMs' ability to recognize arguments under progressively…
With the spread of the use of Text2Img diffusion models such as DALL-E 2, Imagen, Mid Journey and Stable Diffusion, one challenge that artists face is selecting the right prompts to achieve the desired artistic output. We present techniques…
Recent findings in multi-agent deep learning systems point towards the emergence of compositional languages. These claims are often made without exact analysis or testing of the language. In this work, we analyze the emergent language…
Language interpretation is a compositional process, in which the meaning of more complex linguistic structures is inferred from the meaning of their parts. Large language models possess remarkable language interpretation capabilities and…
The goal of this paper is to present a model of children's semantic memory, which is based on a corpus reproducing the kinds of texts children are exposed to. After presenting the literature in the development of the semantic memory, a…
A few million words suffice for children to acquire language. Yet, the brain mechanisms underlying this unique ability remain poorly understood. To address this issue, we investigate neural activity recorded from over 7,400 electrodes…
Large language models are few-shot learners that can solve diverse tasks from a handful of demonstrations. This implicit understanding of tasks suggests that the attention mechanisms over word tokens may play a role in analogical reasoning.…
We present RALL-E, a robust language modeling method for text-to-speech (TTS) synthesis. While previous work based on large language models (LLMs) shows impressive performance on zero-shot TTS, such methods often suffer from poor…
Recent work has shown that distributed word representations can encode abstract information from child-directed speech. In this paper, we use diachronic distributed word representations to perform temporal modeling and analysis of lexical…
We present a novel task and benchmark for evaluating the ability of text-to-image(T2I) generation models to produce images that align with commonsense in real life, which we call Commonsense-T2I. Given two adversarial text prompts…
Large language models (LLMs) have demonstrated remarkable performances on a wide range of natural language tasks. Yet, LLMs' successes have been largely restricted to tasks concerning words, sentences, or documents, and it remains…