arXiv AI

Large Language Models provide support for the parallelogram theory of analogy

arXiv:2603. 19066v2 Announce Type: replace-cross Abstract: Four-term word analogies (A:B::C:D) are classically modeled geometrically as parallelograms: adding the vector B-A+C produces D.

Hugging Face Trending Papers
Aug 4

On the Diversity of Analogy Making in Large Language Models

Large Language Models (LLMs) have demonstrated remarkable potential for analogy making, a core cognitive capability that drives novelty and creativity. While prior research has extensively investigated the applications and underlying mechanisms of LLM-based analogy making, its output diversity remains largely unexplored, despite being essential for broadening cross-domain connections and fostering scientific innovation.

arXiv AI
Jun 26

Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models

arXiv:2601. 03388v3 Announce Type: replace-cross Abstract: Earlier research has shown that metaphors influence human decision-making, raising the question of whether metaphors also influence large language models (LLMs)' reasoning pathways, given that their training data contain a large number of metaphors.

By Zhibo Hu, Chen Wang, Yanfeng Shu, Hye-young Paik, Liming Zhu
arXiv Machine Learning
Jul 1

Symmetry in language statistics shapes the geometry of model representations

arXiv:2602. 15029v3 Announce Type: replace Abstract: The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a circle, historical years form a smooth one-dimensional manifold, and cities' latitudes and longitudes can be decoded using a linear probe.

By Dhruva Karkada, Daniel J. Korchinski, Andres Nava, Matthieu Wyart, Yasaman Bahri
arXiv AI
Jul 21

From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language

arXiv:2607. 16232v1 Announce Type: cross Abstract: The growing use of statistical learning algorithms to infer human preferences from high-dimensional choice data runs up against a fundamental challenge: choice alternatives typically differ in many ways simultaneously, so it is generally unclear which factors actually drove an observed decision and should be credited as preferences.

By Zachary Wojtowicz, Ayush Nayak, Jacob Andreas