Cover Image

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Valentino, Marco, Kim, Geonhee, Dalal, Dhairya, Zhao, Zhixue, Freitas, André
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
by: Quan, Xin, et al.
Published: (2025)

Reasoning with Natural Language Explanations
by: Valentino, Marco, et al.
Published: (2024)

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

Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models
by: Maraia, Gabriele, et al.
Published: (2026)

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

Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models
by: Zhao, Zhixue, et al.
Published: (2024)

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

A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference
by: Thayaparan, Mokanarangan, et al.
Published: (2024)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
by: Weng, Zixuan, et al.
Published: (2026)

A Semantic Search Pipeline for Causality-driven Adhoc Information Retrieval
by: Dalal, Dhairya, et al.
Published: (2025)

LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
by: Rodriguez, Pau, et al.
Published: (2025)

Exploring Vision Language Models for Multimodal and Multilingual Stance Detection
by: Vasilakes, Jake, et al.
Published: (2025)

Activation Scaling for Steering and Interpreting Language Models
by: Stoehr, Niklas, et al.
Published: (2024)

ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models
by: Zhao, Zhixue, et al.
Published: (2024)

Improving Instruction-Following in Language Models through Activation Steering
by: Stolfo, Alessandro, et al.
Published: (2024)

Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning
by: Kabra, Sanchit, et al.
Published: (2025)

Cross-Lingual Activation Steering for Multilingual Language Models
by: Pokharel, Rhitabrat, et al.
Published: (2026)

Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
by: Quan, Xin, et al.
Published: (2025)

Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization
by: Chrysostomou, George, et al.
Published: (2023)

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

Has this Fact been Edited? Detecting Knowledge Edits in Language Models
by: Youssef, Paul, et al.
Published: (2024)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
by: Huang, Yao, et al.
Published: (2025)

Integrating Expert Knowledge into Logical Programs via LLMs
by: Górski, Franciszek, et al.
Published: (2025)

Endogenous Resistance to Activation Steering in Language Models
by: McKenzie, Alex, et al.
Published: (2026)

Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
by: Cheng, Yinjie, et al.
Published: (2025)

ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
by: Guang, Jiahui, et al.
Published: (2026)

Steering Awareness: Detecting Activation Steering from Within
by: Rivera, Joshua Fonseca, et al.
Published: (2025)

GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models
by: Feng, Jiarui, et al.
Published: (2025)

SAKE: Steering Activations for Knowledge Editing
by: Scialanga, Marco, et al.
Published: (2025)

Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
by: Jang, Chaeyun, et al.
Published: (2024)

Improving LLM Reasoning through Interpretable Role-Playing Steering
by: Wang, Anyi, et al.
Published: (2025)

Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya
by: Sathish, Sharath
Published: (2026)

On Effects of Steering Latent Representation for Large Language Model Unlearning
by: Huu-Tien, Dang, et al.
Published: (2024)

Mitigating Overthinking through Reasoning Shaping
by: Song, Feifan, et al.
Published: (2025)

Fine-Grained Self-Endorsement Improves Factuality and Reasoning
by: Wang, Ante, et al.
Published: (2024)

Unveiling Reasoning Thresholds in Language Models: Scaling, Fine-Tuning, and Interpretability through Attention Maps
by: Hsiao, Yen-Che, et al.
Published: (2025)

Self-Steering Language Models
by: Grand, Gabriel, et al.
Published: (2025)

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