Image de couverture de livre

Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Opiełka, Gustaw, Rosenbusch, Hannes, Stevenson, Claire E.
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Causality $\neq$ Invariance: Function and Concept Vectors in LLMs
par: Opiełka, Gustaw, et autres
Publié: (2026)

Do Large Language Models Solve ARC Visual Analogies Like People Do?
par: Opiełka, Gustaw, et autres
Publié: (2024)

Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
par: Hellwig, Philipp, et autres
Publié: (2026)

Evaluating the Robustness of Analogical Reasoning in Large Language Models
par: Lewis, Martha, et autres
Publié: (2024)

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
par: Zheng, Huaixiu Steven, et autres
Publié: (2023)

Function Vectors in Large Language Models
par: Todd, Eric, et autres
Publié: (2023)

Recursive Concept Evolution for Compositional Reasoning in Large Language Models
par: Chaudhry, Sarim
Publié: (2026)

Concept Bottleneck Large Language Models
par: Sun, Chung-En, et autres
Publié: (2024)

Adaptive Task Vectors for Large Language Models
par: Kang, Joonseong, et autres
Publié: (2025)

Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning
par: Ioannou, Antreas, et autres
Publié: (2025)

What makes for an enjoyable protagonist? An analysis of character warmth and competence
par: Rosenbusch, Hannes
Publié: (2026)

When Fairness Isn't Statistical: The Limits of Machine Learning in Evaluating Legal Reasoning
par: Barale, Claire, et autres
Publié: (2025)

Large Language Model Selection with Limited Annotations
par: Durmazkeser, Yavuz, et autres
Publié: (2026)

Model Hemorrhage and the Robustness Limits of Large Language Models
par: Ma, Ziyang, et autres
Publié: (2025)

STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions
par: Fan, Junjie, et autres
Publié: (2025)

Modelling Analogies and Analogical Reasoning: Connecting Cognitive Science Theory and NLP Research
par: Petersen, Molly R, et autres
Publié: (2025)

CLUE: Concept-Level Uncertainty Estimation for Large Language Models
par: Wang, Yu-Hsiang, et autres
Publié: (2024)

Confidence in the Reasoning of Large Language Models
par: Pawitan, Yudi, et autres
Publié: (2024)

Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training
par: Rahmati, Elnaz, et autres
Publié: (2026)

Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses
par: Su, Hung-Ting, et autres
Publié: (2024)

RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
par: Xu, Zukang, et autres
Publié: (2025)

Derivational Morphology Reveals Analogical Generalization in Large Language Models
par: Hofmann, Valentin, et autres
Publié: (2024)

Out-of-Context Reasoning in Large Language Models
par: Shaki, Jonathan, et autres
Publié: (2025)

Exploring Context Window of Large Language Models via Decomposed Positional Vectors
par: Dong, Zican, et autres
Publié: (2024)

Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
par: Yu, Xuemin, et autres
Publié: (2026)

LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models
par: Liu, Tianci, et autres
Publié: (2024)

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
par: Zhao, Haiyan, et autres
Publié: (2024)

LLM_annotate: A Python package for annotating and analyzing fiction characters
par: Rosenbusch, Hannes
Publié: (2025)

Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets
par: Yamashita, Tomoya, et autres
Publié: (2025)

Spectral Generative Flow Models: A Physics-Inspired Replacement for Vectorized Large Language Models
par: Kiruluta, Andrew
Publié: (2026)

Self-Training Large Language Models with Confident Reasoning
par: Jang, Hyosoon, et autres
Publié: (2025)

Benchmarking Large Language Models for Math Reasoning Tasks
par: Seßler, Kathrin, et autres
Publié: (2024)

SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models
par: Cao, Yang, et autres
Publié: (2024)

Beyond Language: Format-Agnostic Reasoning Subspaces in Large Language Models
par: Yuan, Aojie, et autres
Publié: (2026)

Leveraging Large Language Models and Topic Modeling for Toxicity Classification
par: Oskouie, Haniyeh Ehsani, et autres
Publié: (2024)

Are Large Reasoning Models Interruptible?
par: Wu, Tsung-Han, et autres
Publié: (2025)

The Geometry of Categorical and Hierarchical Concepts in Large Language Models
par: Park, Kiho, et autres
Publié: (2024)

Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations
par: Braun, Joschka
Publié: (2026)

Graph Linearization Methods for Reasoning on Graphs with Large Language Models
par: Xypolopoulos, Christos, et autres
Publié: (2024)

FERA: Uncertainty-Aware Federated Reasoning for Large Language Models
par: Wang, Ruhan, et autres
Publié: (2026)