Related papers: Brain-Language Model Alignment: Insights into the …
The mental lexicon is a complex cognitive system representing information about the words/concepts that one knows. Decades of psychological experiments have shown that conceptual associations across multiple, interactive cognitive levels…
Reasoning is an integral part of many tasks performed by language models (LMs). However, the effects of scaling model sizes and data on reasoning abilities at pretraining time remain understudied. To rigorously investigate this problem, we…
Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…
Deep learning has recently made remarkable progress in natural language processing. Yet, the resulting algorithms remain far from competing with the language abilities of the human brain. Predictive coding theory offers a potential…
We introduce a mathematical framework for the linear representation hypothesis (LRH), which asserts that intermediate layers of language models store features linearly. We separate the hypothesis into two claims: linear representation…
The human brain has long inspired the pursuit of artificial intelligence (AI). Recently, neuroimaging studies provide compelling evidence of alignment between the computational representation of artificial neural networks (ANNs) and the…
This paper presents a comprehensive evaluation of the capabilities of Large Language Models (LLMs) in metaphor interpretation across multiple datasets, tasks, and prompt configurations. Although metaphor processing has gained significant…
Brain disorders in the early and late life of humans potentially share pathological alterations in brain functions. However, the key evidence from neuroimaging data for pathological commonness remains unrevealed. To explore this hypothesis,…
This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models…
Natural language interaction with agentic Artificial Intelligence (AI), driven by Large Language Models (LLMs), is expected to remain a dominant paradigm in the near future. While humans instinctively align their communication with mental…
Large Language Models (LLMs) often struggle with deductive judgment in syllogistic reasoning, systematically conflating semantic plausibility with formal validity a phenomenon known as content effect. This bias persists even when models…
The cognitive processes of the hypnotized mind and the computational operations of large language models (LLMs) share deep functional parallels. Both systems generate sophisticated, contextually appropriate behavior through automatic…
Some claim language models understand us. Others won't hear it. To clarify, I investigate three views of human language understanding: as-mapping, as-reliability and as-representation. I argue that while behavioral reliability is necessary…
This comprehensive report distinguishes prior works by the cognitive functions they innovate. Many works claim an almost "human-like" cognitive capability in their world models. To evaluate these claims requires a proper grounding in first…
While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…
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…
Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing…
Situated dialogue requires speakers to maintain a reliable representation of shared context rather than reasoning only over isolated utterances. Current conversational agents often struggle with this requirement, especially when the common…
Pretrained language models (PLMs) have produced substantial improvements in discourse-aware neural machine translation (NMT), for example, improved coherence in spoken language translation. However, the underlying reasons for their strong…