Imagen de Portada

Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Maraia, Gabriele, Valentino, Marco, Zanzotto, Fabio Massimo, Ranaldi, Leonardo
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
por: Ranaldi, Leonardo, et al.
Publicado: (2023)

Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
por: Ranaldi, Leonardo, et al.
Publicado: (2023)

PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
por: Ranaldi, Leonardo, et al.
Publicado: (2023)

Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs
por: Ranaldi, Federico, et al.
Publicado: (2025)

Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations
por: Ranaldi, Leonardo, et al.
Publicado: (2024)

Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages
por: Ruzzetti, Elena Sofia, et al.
Publicado: (2023)

Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation Strategies
por: Jullien, Mael, et al.
Publicado: (2025)

Animate, or Inanimate, That is the Question for Large Language Models
por: Ranaldi, Leonardo, et al.
Publicado: (2024)

Neuro-symbolic Syntactic Parsing: Shaping a Neural Network with the CYK Algorithm
por: Zanzotto, Fabio Massimo, et al.
Publicado: (2026)

Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations
por: Ranaldi, Leonardo, et al.
Publicado: (2025)

Linguistic Fingerprint in Transformer Models: How Language Variation Influences Parameter Selection in Irony Detection
por: Mastromattei, Michele, et al.
Publicado: (2024)

When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour
por: Ranaldi, Leonardo, et al.
Publicado: (2023)

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
por: Valentino, Marco, et al.
Publicado: (2025)

Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrations
por: Ranaldi, Leonardo, et al.
Publicado: (2023)

A Trip Towards Fairness: Bias and De-Biasing in Large Language Models
por: Ranaldi, Leonardo, et al.
Publicado: (2023)

MeMo: Towards Language Models with Associative Memory Mechanisms
por: Zanzotto, Fabio Massimo, et al.
Publicado: (2025)

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models
por: Ruzzetti, Elena Sofia, et al.
Publicado: (2025)

Enhancing Data Privacy in Large Language Models through Private Association Editing
por: Venditti, Davide, et al.
Publicado: (2024)

Reasoning with Natural Language Explanations
por: Valentino, Marco, et al.
Publicado: (2024)

Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation
por: Ranaldi, Federico, et al.
Publicado: (2024)

Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models
por: Tan, Xingwei, et al.
Publicado: (2026)

Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
por: Miranda, Michele, et al.
Publicado: (2024)

Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
por: Ranaldi, Leonardo, et al.
Publicado: (2025)

Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task
por: Ranaldi, Leonardo, et al.
Publicado: (2025)

Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
por: Kim, Geonhee, et al.
Publicado: (2024)

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
por: Yang, Yukang, et al.
Publicado: (2025)

Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models
por: Mastromattei, Michele, et al.
Publicado: (2024)

What is an "Abstract Reasoner"? Revisiting Experiments and Arguments about Large Language Models
por: Yun, Tian, et al.
Publicado: (2025)

Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
por: Xiong, Kai, et al.
Publicado: (2024)

Inference to the Best Explanation in Large Language Models
por: Dalal, Dhairya, et al.
Publicado: (2024)

Every time I fire a conversational designer, the performance of the dialog system goes down
por: Xompero, Giancarlo A., et al.
Publicado: (2021)

Multi-property Steering of Large Language Models with Dynamic Activation Composition
por: Scalena, Daniel, et al.
Publicado: (2024)

A Multi-Stage Workflow for the Review of Marketing Content with Reasoning Large Language Models
por: Purpura, Alberto, et al.
Publicado: (2025)

AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
por: Yeh, Cheng-Kai, et al.
Publicado: (2025)

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
por: Chen, Yuxin, et al.
Publicado: (2025)

SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials
por: Jullien, Mael, et al.
Publicado: (2024)

Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models
por: Ranaldi, Leonardo, et al.
Publicado: (2024)

Navigating Semantic Relations: Challenges for Language Models in Abstract Common-Sense Reasoning
por: Gawin, Cole, et al.
Publicado: (2025)

Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning
por: Pinier, Christopher, et al.
Publicado: (2025)

Towards Context-Invariant Safety Alignment for Large Language Models
por: Wang, Yixu, et al.
Publicado: (2026)