Recently, a boom of papers has shown extraordinary progress in zero-shot and few-shot
learning with various prompt-based models. It is commonly argued that prompts help models …

Recent studies have shown that language models pretrained and/or fine-tuned on randomly
permuted sentences exhibit competitive performance on GLUE, putting into question the …

The field of “BERTology” aims to locate linguistic representations in large language models
(LLMs). These have commonly been interpreted as representing structural descriptions …

Recognizing visual entities in a natural language sentence and arranging them in a 2D
spatial layout require a compositional understanding of language and space. This task of …

While pre-trained language models (PLMs) have shown evidence of acquiring vast amounts
of knowledge, it remains unclear how much of this parametric knowledge is actually usable …

Recent studies have shown that language models pretrained and/or fine-tuned on randomly
permuted sentences exhibit competitive performance on GLUE, putting into question the …

We introduce SPUD (Semantically Perturbed Universal Dependencies), a framework for
creating nonce treebanks for the multilingual Universal Dependencies (UD) corpora. SPUD …

Linear sequences of words are implicitly represented in our brains by hierarchical structures
that organize the composition of words in sentences. Linguists formalize different …

Vision-language models (VLMs), serve as foundation models for multi-modal applications
such as image captioning and text-to-image generation. Recent studies have highlighted …

Recent research has shown that words or morphemes that are closer to each other in linear
order tend to have higher statistical inter-predictability, measured as mutual information. We …