Copertina

Enhancing Cross-task Transfer of Large Language Models via Activation Steering

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tang, Xinyu, Lv, Zhihao, Cheng, Xiaoxue, Li, Junyi, Zhao, Wayne Xin, Wen, Zujie, Zhang, Zhiqiang, Zhou, Jun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
di: Cheng, Xiaoxue, et al.
Pubblicazione: (2025)

ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting
di: Cheng, Xiaoxue, et al.
Pubblicazione: (2024)

Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward
di: Tang, Xinyu, et al.
Pubblicazione: (2025)

Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
di: Cheng, Xiaoxue, et al.
Pubblicazione: (2025)

Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
di: Tang, Xinyu, et al.
Pubblicazione: (2025)

Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering
di: Tang, Xinyu, et al.
Pubblicazione: (2025)

The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
di: Li, Junyi, et al.
Pubblicazione: (2024)

BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models
di: Dong, Zican, et al.
Pubblicazione: (2023)

LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models
di: Yang, Jingyuan, et al.
Pubblicazione: (2025)

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
di: Wang, Xiaolei, et al.
Pubblicazione: (2023)

Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector
di: Cheng, Xiaoxue, et al.
Pubblicazione: (2024)

Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers
di: Tang, Xinyu, et al.
Pubblicazione: (2024)

Exploring Context Window of Large Language Models via Decomposed Positional Vectors
di: Dong, Zican, et al.
Pubblicazione: (2024)

Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering
di: Dong, Fangan, et al.
Pubblicazione: (2026)

DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning
di: Tang, Xinyu, et al.
Pubblicazione: (2024)

A Survey on Long Text Modeling with Transformers
di: Dong, Zican, et al.
Pubblicazione: (2023)

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

Semantic Pivots Enable Cross-Lingual Transfer in Large Language Models
di: He, Kaiyu, et al.
Pubblicazione: (2025)

Improving Conversational Recommendation Systems via Counterfactual Data Simulation
di: Wang, Xiaolei, et al.
Pubblicazione: (2023)

Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning
di: Wang, Xiaolei, et al.
Pubblicazione: (2024)

Neuron-based Personality Trait Induction in Large Language Models
di: Deng, Jia, et al.
Pubblicazione: (2024)

Controlling Large Language Model Agents with Entropic Activation Steering
di: Rahn, Nate, et al.
Pubblicazione: (2024)

LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation
di: Dong, Zican, et al.
Pubblicazione: (2025)

Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment
di: Chen, Zhipeng, et al.
Pubblicazione: (2024)

Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint
di: Chen, Zhipeng, et al.
Pubblicazione: (2024)

How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices
di: Peng, Han, et al.
Pubblicazione: (2025)

Enhancing Large Language Models'Machine Translation via Dynamic Focus Anchoring
di: Ding, Qiuyu, et al.
Pubblicazione: (2025)

LLMBox: A Comprehensive Library for Large Language Models
di: Tang, Tianyi, et al.
Pubblicazione: (2024)

Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment
di: Jiang, Jinhao, et al.
Pubblicazione: (2024)

ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework
di: Huang, Lisheng, et al.
Pubblicazione: (2025)

L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention
di: Zhan, Yuliang, et al.
Pubblicazione: (2025)

Steering Large Language Models with Register Analysis for Arbitrary Style Transfer
di: Yang, Xinchen, et al.
Pubblicazione: (2025)

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning
di: Yan, Yuchen, et al.
Pubblicazione: (2026)

Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
di: Sun, Haoxiang, et al.
Pubblicazione: (2025)

Activation Steering for Masked Diffusion Language Models
di: Shnaidman, Adi, et al.
Pubblicazione: (2025)

Contextual Linear Activation Steering of Language Models
di: Hsu, Brandon, et al.
Pubblicazione: (2026)

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

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models
di: Sun, Yuchong, et al.
Pubblicazione: (2023)

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
di: Li, Yifan, et al.
Pubblicazione: (2024)

Self-Translate-Train: Enhancing Cross-Lingual Transfer of Large Language Models via Inherent Capability
di: Ri, Ryokan, et al.
Pubblicazione: (2024)