arXiv Computation and Language August 27, 2026 By Casey Kennington

A Primer on Computational Semantics for Artificial Intelligence Systems

Read the original on arXiv Computation and Language →

The article "A Primer on Computational Semantics for Artificial Intelligence Systems" introduces the importance of understanding how transformer-based language models learn and represent meaning as they become more widely used. It surveys linguistic meaning from scientific and philosophical perspectives, outlines three main semantic theories—formal, grounded, and distributional—and compares these theories to how humans acquire language.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

llms

arXiv Computation and Language

Sep 18

Generalization through Lexical Abstraction in Transformer Models: The Case of Functional Words

The study investigates whether pretrained transformer models encode functional words—such as pronouns and adverbs—in a way that mirrors human usage. By comparing embeddings of nouns with those of their functional counterparts in both isolated and parallel sentences, the authors find that functional words occupy a central yet distinct position in embedding space and that parallel lexicalized and functional sentences reside in different subspaces. Experiments show that only a mixed training set of functional and lexicalized sentences reveals shared syntactic and semantic structure, whereas training on either type alone fails to capture this parallelism.

By Giuseppe Samo, Vivi Nastase, Paola Merlo

llms rag

arXiv Computation and Language

4d ago

Co-Linguistics: AI-augmented Theory Construction in Linguistics

arXiv:2609.37635v1 Announce Type: new Abstract: LLMs have been studied in recent linguistics as potential models of humans' linguistic abilities. Here we discuss an entirely different use of AI, name...

By Emmanuel Chemla, Benjamin Spector, Alexandros Kalomoiros, Philippe Schlenker

llms agents

arXiv AI

Sep 1

The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models

arXiv:2601.19926v3 Announce Type: replace-cross Abstract: We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on o...

By Nora Graichen, Iria de-Dios-Flores, Gemma Boleda

llms safety

arXiv Machine Learning

Jul 14

One mechanism for many mental spaces: a shared router over a value slot in language models

arXiv:2607. 10248v1 Announce Type: cross Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical.

By Oliver Steele, Jiangtao Wen, Yuxing Han

llms safety

arXiv AI

Sep 12

Some hypotheses on how chatbots work in problem-solution-driven conversations: Large Language Models as confirmation of the Innovation Illusion

The article examines chatbots as partners in problem‑solving conversations, arguing that basic chatbots—comprising a large language model (LLM) and a simple interface—are multifaceted but cannot match human cognitive flexibility. Drawing on Aggregation Dynamics, Cognitive Linguistics, Neuropsychology, and Psychology, the authors describe how LLMs encode artificial metaphorical problem propagations from training data, which only partially imitate human thinking. They conclude that further LLM development will not yield true thinking partners, yet chatbots are widely used, making their understanding socially and politically important.

By S. F. M. van Vlijmen, H. D. Lethe jr

llms

arXiv Machine Learning

Jun 15

A theoretical model for task routing in mixture-of-expert transformers

arXiv:2606. 14398v1 Announce Type: new Abstract: Mixture-of-experts (MoE) layers enable the scaling of transformer models while keeping the inference compute fixed.

By Yongli Xiang, Vinoth Nandakumar, Yunzhi Yao, Peike Li, Tongliang Liu