Copertina

A Unified Understanding and Evaluation of Steering Methods

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Im, Shawn, Li, Sharon
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
di: Im, Shawn, et al.
Pubblicazione: (2026)

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
di: Oh, Changdae, et al.
Pubblicazione: (2025)

Towards Understanding Steering Strength
di: Taimeskhanov, Magamed, et al.
Pubblicazione: (2026)

Can DPO Learn Diverse Human Values? A Theoretical Scaling Law
di: Im, Shawn, et al.
Pubblicazione: (2024)

How Well Can Preference Optimization Generalize Under Noisy Feedback?
di: Im, Shawn, et al.
Pubblicazione: (2025)

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

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

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

Beyond Multiple Choice: Evaluating Steering Vectors for Summarization
di: Braun, Joschka, et al.
Pubblicazione: (2025)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
di: Siu, Vincent, et al.
Pubblicazione: (2025)

Understanding and Mitigating Dataset Corruption in LLM Steering
di: Anderson, Cullen, et al.
Pubblicazione: (2026)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
di: Oozeer, Narmeen, et al.
Pubblicazione: (2025)

Cyclical Entropy Eruption: Entropy Dynamics in Agent Reinforcement Learning
di: Li, Wendi, et al.
Pubblicazione: (2026)

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
di: Zhang, Zhenyu, et al.
Pubblicazione: (2025)

Conceptors for Semantic Steering
di: Triantafyllopoulos, Ilias, et al.
Pubblicazione: (2026)

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

Understanding the Learning Dynamics of Alignment with Human Feedback
di: Im, Shawn, et al.
Pubblicazione: (2024)

That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation
di: Bae, Jaesung, et al.
Pubblicazione: (2025)

A Unified Benchmark for Evaluating Knowledge Graph Construction Methods and Graph Neural Networks
di: Kabal, Othmane, et al.
Pubblicazione: (2026)

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
di: Cao, Yuanpu, et al.
Pubblicazione: (2024)

A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation
di: He, Haonan, et al.
Pubblicazione: (2026)

ILRR: Inference-Time Steering Method for Masked Diffusion Language Models
di: Avrahami, Eden, et al.
Pubblicazione: (2026)

Steering Language Models with Weight Arithmetic
di: Fierro, Constanza, et al.
Pubblicazione: (2025)

Predicting Where Steering Vectors Succeed
di: Billa, Jayadev
Pubblicazione: (2026)

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

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

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

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
di: Li, Zihao, et al.
Pubblicazione: (2025)

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

Compositional Steering of Large Language Models with Steering Tokens
di: Radevski, Gorjan, et al.
Pubblicazione: (2026)

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
di: Cheng, Stephen, et al.
Pubblicazione: (2026)

UALM: Unified Audio Language Model for Understanding, Generation and Reasoning
di: Tian, Jinchuan, et al.
Pubblicazione: (2025)

Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
di: Deng, Wenlong, et al.
Pubblicazione: (2025)

Evaluating Copyright Takedown Methods for Language Models
di: Wei, Boyi, et al.
Pubblicazione: (2024)

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
di: Gan, Woody Haosheng, et al.
Pubblicazione: (2025)

Differentially Private Steering for Large Language Model Alignment
di: Goel, Anmol, et al.
Pubblicazione: (2025)

VSPO: Vector-Steered Policy Optimization for Behavioral Control
di: Zhang, Xuechen, et al.
Pubblicazione: (2026)

ROAST: Rollout-based On-distribution Activation Steering Technique
di: Su, Xuanbo, et al.
Pubblicazione: (2026)

Social Caption: Evaluating Social Understanding in Multimodal Models
di: Thumu, Bhaavanaa, et al.
Pubblicazione: (2026)

Steer LLM Latents for Hallucination Detection
di: Park, Seongheon, et al.
Pubblicazione: (2025)