Related papers: Meaning-infused grammar: Gradient Acceptability Sh…

Since their introduction, Transformer architectures have dominated Natural Language Processing (NLP). However, recent research has highlighted an inherent anisotropy phenomenon in these models, presenting a significant challenge to their…

In-context learning (ICL) enables large language models (LLMs) to acquire new behaviors from the input sequence alone without any parameter updates. Recent studies have shown that ICL can surpass the original meaning learned in pretraining…

Understanding how Transformer-based Language Models (LMs) learn and recall information is a key goal of the deep learning community. Recent interpretability methods project weights and hidden states obtained from the forward pass to the…

Grounding the common-sense reasoning of Large Language Models (LLMs) in physical domains remains a pivotal yet unsolved problem for embodied AI. Whereas prior works have focused on leveraging LLMs directly for planning in symbolic spaces,…

Large language models (LLMs) are increasingly used as evaluators for natural language generation, applying human-defined rubrics to assess system outputs. However, human rubrics are often static and misaligned with how models internally…

Existing text representations such as embeddings and bag-of-words are not suitable for rule learning due to their high dimensionality and absent or questionable feature-level interpretability. This article explores whether large language…

Advancing towards artificial superintelligence requires rich and intelligent perceptual capabilities. A critical frontier in this pursuit is overcoming the limited spatial understanding of Multimodal Large Language Models (MLLMs), where…

Abstract concepts - justice, theory, availability - have no single perceivable referent; in the human brain, their meaning emerges from a web of experiences, affect, and social context. Do large language models (LLMs) ground abstract…

This paper presents a systematic evaluation of state-of-the-art multimodal large language models (MLLMs) on intuitive physics tasks using the GRASP and IntPhys 2 datasets. We assess the open-source models InternVL 2.5, Qwen 2.5 VL,…

Multimodal large language models (MLLMs) have made significant progress in integrating visual and linguistic understanding. Existing benchmarks typically focus on high-level semantic capabilities, such as scene understanding and visual…

Large Language Models (LLMs) are increasingly used as proxy students in the development of Intelligent Tutoring Systems (ITSs) and in piloting test questions. However, to what extent these proxy students accurately emulate the behavior and…

Large language models (LLMs) generalize smoothly across continuous semantic spaces, yet strict logical reasoning demands the formation of discrete decision boundaries. Prevailing theories relying on linear isometric projections fail to…

Applying AI foundation models directly to geospatial datasets remains challenging due to their limited ability to represent and reason with geographical entities, specifically vector-based geometries and natural language descriptions of…

Pre-trained word embeddings are widely used for transfer learning in natural language processing. The embeddings are continuous and distributed representations of the words that preserve their similarities in compact Euclidean spaces.…

A prior-informed large language model (LLM) driven multi-task learning framework is proposed for the unified description of multiple nuclear observables. By fine-tuning the pre-trained DeepSeek-R1-1.5B model with Low-Rank Adaptation (LoRA),…

Neural network models of language have long been used as a tool for developing hypotheses about conceptual representation in the mind and brain. For many years, such use involved extracting vector-space representations of words and using…

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Recent work found high mutual information between the learned representations of large language models (LLMs) and the geospatial property of its input, hinting an emergent internal model of space. However, whether this internal space model…

Large Language Models are transformer neural networks which are trained to produce a probability distribution on the possible next words to given texts in a corpus, in such a way that the most likely word predicted is the actual word in the…

Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific level of linguistic unit, which cause great inconvenience when being confronted with handling multiple…