Copertina

Activation Steering for Chain-of-Thought Compression

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Azizi, Seyedarmin, Potraghloo, Erfan Baghaei, Pedram, Massoud
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
di: Potraghloo, Erfan Baghaei, et al.
Pubblicazione: (2025)

One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness
di: Potraghloo, Erfan Baghaei, et al.
Pubblicazione: (2026)

Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning
di: Azizi, Seyedarmin, et al.
Pubblicazione: (2026)

Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy
di: Azizi, Seyedarmin, et al.
Pubblicazione: (2024)

LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation
di: Azizi, Seyedarmin, et al.
Pubblicazione: (2024)

Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators
di: Azizi, Seyedarmin, et al.
Pubblicazione: (2024)

Sensitivity-Aware Mixed-Precision Quantization and Width Optimization of Deep Neural Networks Through Cluster-Based Tree-Structured Parzen Estimation
di: Azizi, Seyedarmin, et al.
Pubblicazione: (2023)

VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis
di: Khezresmaeilzadeh, Tina, et al.
Pubblicazione: (2025)

Training-Free Acceleration of ViTs with Delayed Spatial Merging
di: Heo, Jung Hwan, et al.
Pubblicazione: (2023)

SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models
di: Tian, Jiayi, et al.
Pubblicazione: (2025)

PEANO-ViT: Power-Efficient Approximations of Non-Linearities in Vision Transformers
di: Sadeghi, Mohammad Erfan, et al.
Pubblicazione: (2024)

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
di: Batra, Shourya, et al.
Pubblicazione: (2025)

Dynamic Co-Optimization Compiler: Leveraging Multi-Agent Reinforcement Learning for Enhanced DNN Accelerator Performance
di: Fayyazi, Arya, et al.
Pubblicazione: (2024)

FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems
di: Fayyazi, Arya, et al.
Pubblicazione: (2025)

COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models
di: Fayyazi, Arya, et al.
Pubblicazione: (2026)

Long Chain-of-Thought Compression via Fine-Grained Group Policy Optimization
di: Han, Xinchen, et al.
Pubblicazione: (2026)

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

Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization
di: Li, Hanyu, et al.
Pubblicazione: (2025)

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)

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

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

When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing
di: Dadfar, Zachary Pedram
Pubblicazione: (2026)

Ehrenfeucht-Haussler Rank and Chain of Thought
di: Barceló, Pablo, et al.
Pubblicazione: (2025)

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

The Rogue Scalpel: Activation Steering Compromises LLM Safety
di: Korznikov, Anton, et al.
Pubblicazione: (2025)

Test-time Diverse Reasoning by Riemannian Activation Steering
di: Khanh, Ly Tran Ho, et al.
Pubblicazione: (2025)

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

CBMAS: Cognitive Behavioral Modeling via Activation Steering
di: Ismail, Ahmed H., et al.
Pubblicazione: (2026)

Chain-of-Thought Predictive Control
di: Jia, Zhiwei, et al.
Pubblicazione: (2023)

Unveiling Confirmation Bias in Chain-of-Thought Reasoning
di: Wan, Yue, et al.
Pubblicazione: (2025)

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

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
di: Zaman, Kerem, et al.
Pubblicazione: (2025)

Dynamic Chain-of-Thought: Towards Adaptive Deep Reasoning
di: Wang, Libo
Pubblicazione: (2025)

Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics
di: Sheng, Leheng, et al.
Pubblicazione: (2026)

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

Programming Refusal with Conditional Activation Steering
di: Lee, Bruce W., et al.
Pubblicazione: (2024)

Exploring the In-Context Learning Capabilities of LLMs for Money Laundering Detection in Financial Graphs
di: Pirmorad, Erfan
Pubblicazione: (2025)

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

Fractured Chain-of-Thought Reasoning
di: Liao, Baohao, et al.
Pubblicazione: (2025)