相关论文: Towards Human Cognition: Visual Context Guides Syn…

We investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how…

Neural language models (LMs) perform well on tasks that require sensitivity to syntactic structure. Drawing on the syntactic priming paradigm from psycholinguistics, we propose a novel technique to analyze the representations that enable…

The syntactic structures of sentences can be readily read-out from the activations of large language models (LLMs). However, the ``structural probes'' that have been developed to reveal this phenomenon are typically evaluated on an…

We explore which linguistic factors -- at the sentence and token level -- play an important role in influencing language model predictions, and investigate whether these are reflective of results found in humans and human corpora (Gries and…

Abstract grammatical knowledge - of parts of speech and grammatical patterns - is key to the capacity for linguistic generalization in humans. But how abstract is grammatical knowledge in large language models? In the human literature,…

Multimodal sentiment analysis (MSA) aims to predict human sentiment from textual, acoustic, and visual information in videos. Recent studies improve multimodal fusion by modeling modality interaction and assigning different modality…

Structural priming is a widely used psycholinguistic paradigm to study human sentence representations. In this work we introduce SPAWN, a cognitively motivated parser that can generate quantitative priming predictions from contemporary…

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce…

Syntactic parsing is the task of assigning a syntactic structure to a sentence. There are two popular syntactic parsing methods: constituency and dependency parsing. Recent works have used syntactic embeddings based on constituency trees,…

We study how prompt-level inductive biases influence the cognitive behavior of large language models (LLMs) in instructional dialogue. We introduce a symbolic scaffolding method paired with a short-term memory schema designed to promote…

Language models have been shown to be very effective in predicting brain recordings of subjects experiencing complex language stimuli. For a deeper understanding of this alignment, it is important to understand the correspondence between…

Establishing stable mappings between natural language expressions and visual percepts is a foundational problem for both cognitive science and artificial intelligence. Humans routinely ground linguistic reference in noisy, ambiguous…

Large Language Models (LLMs) are machine learning models that have seen widespread adoption due to their capability of handling previously difficult tasks. LLMs, due to their training, are sensitive to how exactly a question is presented,…

Deciphering how visual stimuli are transformed into cortical responses is a fundamental challenge in computational neuroscience. This visual-to-neural mapping is inherently a one-to-many relationship, as identical visual inputs reliably…

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

A central question in psycholinguistics is the timing of syntax in sentence processing. Much of the existing evidence comes from violation paradigms, which conflate two separable processes - syntactic category detection and phrase structure…

People exploit the predictability of lexical structures during text comprehension. Though predictable structure is also present in speech, the degree to which prosody, e.g. intonation, tempo, and loudness, contributes to such structure…

Existing driving style recognition systems largely depend on low-level sensor-derived features for training, neglecting the rich semantic reasoning capability inherent to human experts. This discrepancy results in a fundamental misalignment…

Leveraging the perceptual phenomenon of crossmoal correspondence has been shown to facilitate peoples information processing and improves sensorimotor performance. However for goal-oriented interactive tasks, the question of how to enhance…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models to downstream tasks. As large language models (LLMs) have emerged, recent studies have explored the use of category-related descriptions as input…