Cover Image

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Birong, Xu, Mayi, Pi, Qiankun, Chen, Jianhao, Zhu, Yuanyuan, Zhong, Ming, Qian, Tieyun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data
by: Liu, Jiacheng, et al.
Published: (2025)

A Survey on Training-free Alignment of Large Language Models
by: Pan, Birong, et al.
Published: (2025)

Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question Answering
by: Ning, Yunfeng, et al.
Published: (2025)

Can a Small Model Learn to Look Before It Leaps? Dynamic Learning and Proactive Correction for Hallucination Detection
by: Bao, Zepeng, et al.
Published: (2025)

Aligning VLM Assistants with Personalized Situated Cognition
by: Li, Yongqi, et al.
Published: (2025)

Toxicity Detection towards Adaptability to Changing Perturbations
by: Kang, Hankun, et al.
Published: (2024)

NeuronTune: Towards Self-Guided Spurious Bias Mitigation
by: Zheng, Guangtao, et al.
Published: (2025)

Prompting Large Language Models for Counterfactual Generation: An Empirical Study
by: Li, Yongqi, et al.
Published: (2023)

Beyond Static Snapshots: Dynamic Modeling and Forecasting of Group-Level Value Evolution with Large Language Models
by: Pi, Qiankun, et al.
Published: (2026)

Reasoning based on symbolic and parametric knowledge bases: a survey
by: Xu, Mayi, et al.
Published: (2025)

ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations
by: Kang, Hankun, et al.
Published: (2026)

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations
by: Li, Xiaohu, et al.
Published: (2025)

Enhancing Relation Extraction via Supervised Rationale Verification and Feedback
by: Li, Yongqi, et al.
Published: (2024)

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning
by: Yi, Xin, et al.
Published: (2024)

Let's Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model
by: Xu, Haoyun, et al.
Published: (2024)

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
by: Chen, Jianhui, et al.
Published: (2024)

Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
by: Pan, Haowen, et al.
Published: (2025)

From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment
by: Huang, Chongxuan, et al.
Published: (2025)

LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation
by: Zhu, Shaolin, et al.
Published: (2024)

Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding
by: Zhu, Yunchang, et al.
Published: (2023)

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
by: Kazemi, Hamid, et al.
Published: (2026)

H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
by: Gao, Cheng, et al.
Published: (2025)

Truth Neurons
by: Li, Haohang, et al.
Published: (2025)

NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning
by: Zhang, Zhi, et al.
Published: (2025)

AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models
by: Kang, Hankun, et al.
Published: (2026)

How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective
by: Zhang, Shimao, et al.
Published: (2025)

RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
by: Chen, Jianhao, et al.
Published: (2025)

On the Relationship between Skill Neurons and Robustness in Prompt Tuning
by: Ackermann, Leon, et al.
Published: (2023)

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
by: Giordani, Jeremiah
Published: (2025)

Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation
by: Jiang, Shuting, et al.
Published: (2026)

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
by: Zhang, Zhuoxuan, et al.
Published: (2025)

Improving Generalization in LLM Structured Pruning via Function-Aware Neuron Grouping
by: Yu, Tao, et al.
Published: (2025)

Fine-Tuning LLMs with Fine-Grained Human Feedback on Text Spans
by: CH-Wang, Sky, et al.
Published: (2025)

NEAT: Concept driven Neuron Attribution in LLMs
by: Kavuri, Vivek Hruday, et al.
Published: (2025)

SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
by: Wang, Zhaoxin, et al.
Published: (2026)

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
by: Pang, Jinlong, et al.
Published: (2025)

Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs
by: Wang, Weixuan, et al.
Published: (2024)

Style-Specific Neurons for Steering LLMs in Text Style Transfer
by: Lai, Wen, et al.
Published: (2024)

Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors
by: Tsuji, Kohei, et al.
Published: (2025)

Neuron-Aware Data Selection In Instruction Tuning For Large Language Models
by: Chen, Xin, et al.
Published: (2026)