Instruction tuning aligns the response of large language models (LLMs) with human
preferences. Despite such efforts in human--LLM alignment, we find that instruction tuning …

We introduce Holmes, a new benchmark designed to assess language models'(LMs')
linguistic competence—their unconscious understanding of linguistic phenomena …

Noun-noun compounds interpretation is the task where a model is given one of such
constructions, and it is asked to provide a paraphrase, making the semantic relation …

Large Language Models (LLMs) have been shown to be effective models of the human
language system, with some models predicting most explainable variance of brain activity in …

Recent cognitive modeling studies have reported that larger language models (LMs) exhibit
a poorer fit to human reading behavior, leading to claims of their cognitive implausibility. In …

Semantic plausibility (eg knowing that" the actor won the award" is more likely than" the
actor won the battle") serves as an effective proxy for general world knowledge. Language …

Large language models (LLMs) are very performant connectionist systems, but do they
exhibit more compositionality? More importantly, is that part of why they perform so well? We …

Large Vision-Language Models (LVLMs) typically learn visual capacity through visual
instruction tuning, involving updates to both a projector and their LLM backbones. Drawing …

Many studies have evaluated the cognitive alignment of Pre-trained Language Models
(PLMs), ie, their correspondence to adult performance across a range of cognitive domains …

The association between language and (non-linguistic) thinking ability in humans has long
been debated, and recently, neuroscientific evidence of brain activity patterns has been …