Analogical Reasoning for Language Models

Follow this topic Ask about this topic

Latest papers

15 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Archetypal contexts in the neurons of language models: an architecture for intelligence?
Nov 4, 2026David NordforsAnalogical Reasoning for Language Models Concept Localization in Language Models
ARCANA: A Benchmark for Abstraction and Analogical Reasoning
Oct 21, 2026Ruqi Chen, Zilei Wang, Wei WangAnalogical Reasoning for Language Models Language Model Reasoning Evaluation
University of Science and Technology of China, Hefei, China · State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China · University of Science and Technology Beijing, Beijing, China
On the Diversity of Analogy Making in Large Language Models
Aug 4, 2026Yuanhao Shen, Daniel Xavier de Sousa, Caio César Sifuentes Barcelos +2LLM Evaluation Analogical Reasoning for Language Models
Department of Electrical and Computer Engineering & Ingenuity Labs Research Institute, Queen’s University, Canada · Instituto Federal de Goiás, Anápolis, Brazil · National Research Council Canada.
ADAGE: A Language-Agnostic Pipeline for Analogical Reasoning Evaluation
Jul 25, 2026Ahmed Haj Ahmed, Alvin GrissomMultilingual Language Model Evaluation Reasoning Evaluation
Haverford College
Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis
Jul 15, 2026Yongqiang Chen, Guangyi Chen, Yuewen Sun +1Analogical Reasoning for Language Models Analogical Reasoning
1Mohamed bin Zayed University of Artificial Intelligence · 2Carnegie Mellon University
The Metanym Game: A Self-Contained, Self-Consistent LLM Peer-Community Benchmark for Structural Intelligence
Jun 19, 2026David NordforsLLM Evaluation LLM-as-a-Judge
Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning
Jun 11, 2026Zilin Xiao, Qi Ma, Chun-cheng Jason Chen +4Analogical Reasoning RL for Language Model Reasoning
Meta Superintelligence Labs · Rice University · Work partially done during internship at Meta
Teaching Through Analogies: A Modular Pipeline for Educational Analogy Generation
May 22, 2026Mariam Barakat, Ekaterina KochmarLLM Evaluation LLM Grounding
Mohamed bin Zayed University of Artificial Intelligence, UAE
Enhancing Agent Safety Judgment: Controlled Benchmark Rewriting and Analogical Reasoning for Deceptive Out-of-Distribution Scenarios
May 5, 2026Zuoyu Zhang, Yancheng ZhuAnalogical Reasoning for Language Models AI Agent Safety
Shenzhen University, Shenzhen, China.
CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation
Apr 12, 2026Bingzhe Wu, Haotian Lu, Yuchen MouAnalogical Reasoning for Language Models Content Moderation
Shenzhen University · Tsinghua University · National University of Singapore
CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs
Apr 12, 2026Haotian Lu, Yuchen Mou, Bingzhe WuAnalogical Reasoning for Language Models Content Moderation
Shenzhen University · Tsinghua University · National University of Singapore
Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
Apr 7, 2026Philipp Hellwig, Willem Zuidema, Claire E. Stevenson +1Analogical Reasoning for Language Models Compositional Generalization
Psychological Methods, University of Amsterdam · Institute for Logic, Language and Computation, University of Amsterdam
When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
Apr 4, 2026Hope McGovern, Caroline Craig, Thomas Lippincott +1Analogical Reasoning for Language Models LLM Reasoning
Cambridge University · Northeastern University · Athenahealth +1
Large Language Models provide support for the parallelogram theory of analogy
Mar 19, 2026Qiawen Ella Liu, Raja Marjieh, Jian-Qiao Zhu +2Analogical Reasoning for Language Models Analogical Reasoning
Princeton University · The University of Hong Kong
Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers
Mar 5, 2026Ruichen Xu, Wenjing Yan, Ying-Jun Angela ZhangAnalogical Reasoning Analogical Reasoning for Language Models
Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong.

Nov 4, 2026J/K move · Enter open · S save

Archetypal contexts in the neurons of language models: an architecture for intelligence?

David Nordfors

Analogical Reasoning for Language Models Concept Localization in Language Models Disentangled Representation Learning

Open paper AskPDF arXiv

We validate our previous hypothesis that a language model holds relational patterns apart from the subject domains that instantiate them (Nordfors, 2026). These archetypal contexts are patterns of relations that people recognize across many fields, such as the tipping point or winner takes all, held once and applied across domains. We show this inside the model, Qwen3.8-27B. One set of neurons carries the archetype, say the tipping point; another carries the topic, say politics, ecology or cell biology; a third carries the language, such as English, Spanish or Chinese. Silence the tipping point's neurons, and the model no longer identifies the pattern but still knows what the text is about. Silence the topic's, and it loses the topic but still names the pattern. In the neuron maps the layers organize themselves into a sandwich: the outer layers carry languages, the layers inside them topics, the layers at the heart archetypes. The sandwich emerges spontaneously during pretraining and appears in every model we mapped. Archetypes are the architecture for analogy, and we strongly suggest that this structure of archetypes and topics is the mechanism of a language model's intelligence: we see it self-organize as the model is trained. The neurons, the texts and the code are released with this paper as its reproduction package, so that anyone can repeat the test inside the model.