Copertina

Steering Code LLMs with Activation Directions for Language and Library Control

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rahman, Md Mahbubur, Guha, Arjun, Menon, Harshitha
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation
di: Zi, Yangtian, et al.
Pubblicazione: (2025)

Understanding How CodeLLMs (Mis)Predict Types with Activation Steering
di: Lucchetti, Francesca, et al.
Pubblicazione: (2024)

Emotion Detection From Social Media Posts
di: Rahman, Md Mahbubur, et al.
Pubblicazione: (2023)

Substance Beats Style: Why Beginning Students Fail to Code with LLMs
di: Lucchetti, Francesca, et al.
Pubblicazione: (2024)

Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs
di: Hegazy, Amr, et al.
Pubblicazione: (2025)

Activation Steering with a Feedback Controller
di: Nguyen, Dung V., et al.
Pubblicazione: (2025)

Relative Positioning Based Code Chunking Method For Rich Context Retrieval In Repository Level Code Completion Task With Code Language Model
di: Rahman, Imranur, et al.
Pubblicazione: (2025)

Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs
di: Cassano, Federico, et al.
Pubblicazione: (2023)

Steering Language Models With Activation Engineering
di: Turner, Alexander Matt, et al.
Pubblicazione: (2023)

SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models
di: Sivakumar, Anushka, et al.
Pubblicazione: (2025)

Depth-Wise Activation Steering for Honest Language Models
di: Góral, Gracjan, et al.
Pubblicazione: (2025)

Steering MoE LLMs via Expert (De)Activation
di: Fayyaz, Mohsen, et al.
Pubblicazione: (2025)

Extracting Unlearned Information from LLMs with Activation Steering
di: Seyitoğlu, Atakan, et al.
Pubblicazione: (2024)

Elevating Intrusion Detection and Security Fortification in Intelligent Networks through Cutting-Edge Machine Learning Paradigms
di: Munna, Md Minhazul Islam, et al.
Pubblicazione: (2025)

Automated Neuron Labelling Enables Generative Steering and Interpretability in Protein Language Models
di: Banerjee, Arjun, et al.
Pubblicazione: (2025)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
di: Jiang, Xinyan, et al.
Pubblicazione: (2026)

Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
di: Kang, Minjae, et al.
Pubblicazione: (2026)

Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment
di: Boruch-Gruszecki, Aleksander, et al.
Pubblicazione: (2025)

Steering Large Language Model Activations in Sparse Spaces
di: Bayat, Reza, et al.
Pubblicazione: (2025)

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

Angular Steering: Behavior Control via Rotation in Activation Space
di: Vu, Hieu M., et al.
Pubblicazione: (2025)

SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs
di: Ghosh, Shaona, et al.
Pubblicazione: (2025)

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
di: You, Zejia, et al.
Pubblicazione: (2026)

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
di: Skifstad, Julian, et al.
Pubblicazione: (2026)

SteerConf: Steering LLMs for Confidence Elicitation
di: Zhou, Ziang, et al.
Pubblicazione: (2025)

Dynamically Scaled Activation Steering
di: Ferrando, Alex, et al.
Pubblicazione: (2025)

HyperSteer: Activation Steering at Scale with Hypernetworks
di: Sun, Jiuding, et al.
Pubblicazione: (2025)

A Unifying Human-Centered AI Fairness Framework
di: Rahman, Munshi Mahbubur, et al.
Pubblicazione: (2025)

LeMo-NADe: Multi-Parameter Neural Architecture Discovery with LLMs
di: Rahman, Md Hafizur, et al.
Pubblicazione: (2024)

Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
di: Yang, Jiaxi, et al.
Pubblicazione: (2026)

Steer Like the LLM: Activation Steering that Mimics Prompting
di: Heyman, Geert, et al.
Pubblicazione: (2026)

Minimizing Collateral Damage in Activation Steering
di: Nguyen, Tam, et al.
Pubblicazione: (2026)

Steered LLM Activations are Non-Surjective
di: Mishra, Aayush, et al.
Pubblicazione: (2026)

Activation Steering for Chain-of-Thought Compression
di: Azizi, Seyedarmin, et al.
Pubblicazione: (2025)

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

Aligning CodeLLMs with Direct Preference Optimization
di: Miao, Yibo, et al.
Pubblicazione: (2024)

Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
di: Jones, Erik, et al.
Pubblicazione: (2025)

Towards Causal Deep Learning for Vulnerability Detection
di: Rahman, Md Mahbubur, et al.
Pubblicazione: (2023)

How a Bit Becomes a Story: Semantic Steering via Differentiable Fault Injection
di: Haider, Zafaryab, et al.
Pubblicazione: (2025)

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
di: Jin, Zehao, et al.
Pubblicazione: (2026)