Cover Image

Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Mengru, Xu, Ziwen, Mao, Shengyu, Deng, Shumin, Tu, Zhaopeng, Chen, Huajun, Zhang, Ningyu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Information Retrieval Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Data to Behavior: Predicting Unintended Model Behaviors Before Training
by: Wang, Mengru, et al.
Published: (2026)

Knowledge Circuits in Pretrained Transformers
by: Yao, Yunzhi, et al.
Published: (2024)

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
by: Xu, Ziwen, et al.
Published: (2026)

Automating Steering for Safe Multimodal Large Language Models
by: Wu, Lyucheng, et al.
Published: (2025)

Editing Conceptual Knowledge for Large Language Models
by: Wang, Xiaohan, et al.
Published: (2024)

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
by: Wang, Peng, et al.
Published: (2023)

LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities
by: Zhu, Yuqi, et al.
Published: (2023)

Towards A Unified View of Answer Calibration for Multi-Step Reasoning
by: Deng, Shumin, et al.
Published: (2023)

RaFe: Ranking Feedback Improves Query Rewriting for RAG
by: Mao, Shengyu, et al.
Published: (2024)

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
by: Wang, Mengru, et al.
Published: (2025)

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
by: Yao, Yunzhi, et al.
Published: (2025)

Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
by: Chen, Xiang, et al.
Published: (2025)

Information Extraction in Low-Resource Scenarios: Survey and Perspective
by: Deng, Shumin, et al.
Published: (2022)

CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs
by: Fang, Jizhan, et al.
Published: (2024)

WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
by: Wang, Peng, et al.
Published: (2024)

StructMem: Structured Memory for Long-Horizon Behavior in LLMs
by: Xu, Buqiang, et al.
Published: (2026)

SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
by: Qiao, Shuofei, et al.
Published: (2026)

Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation
by: Deng, Chenlong, et al.
Published: (2024)

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
by: Zhang, Jintian, et al.
Published: (2024)

All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution
by: Lv, Can, et al.
Published: (2026)

EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models
by: Ou, Yixin, et al.
Published: (2024)

Making Language Models Better Tool Learners with Execution Feedback
by: Qiao, Shuofei, et al.
Published: (2023)

Few-Shot Prompting for Extractive Quranic QA with Instruction-Tuned LLMs
by: Basem, Mohamed, et al.
Published: (2025)

Prompt-Based LLMs for Position Bias-Aware Reranking in Personalized Recommendations
by: Islam, Md Aminul, et al.
Published: (2025)

ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval
by: Mao, Kelong, et al.
Published: (2024)

Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval
by: Chen, Hung-Ting, et al.
Published: (2025)

Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
by: Sinha, Aarush
Published: (2025)

OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
by: Zhang, Ningyu, et al.
Published: (2024)

Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
by: Zhao, Ziyi, et al.
Published: (2026)

Improving Topic Relevance Model by Mix-structured Summarization and LLM-based Data Augmentation
by: Liu, Yizhu, et al.
Published: (2024)

Corpus-Steered Query Expansion with Large Language Models
by: Lei, Yibin, et al.
Published: (2024)

RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects
by: Tu, Yiteng, et al.
Published: (2025)

Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
by: Liu, Peiyang, et al.
Published: (2026)

Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach
by: Zeng, Shenglai, et al.
Published: (2025)

IEPile: Unearthing Large-Scale Schema-Based Information Extraction Corpus
by: Gui, Honghao, et al.
Published: (2024)

Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study
by: Zhu, Yuqi, et al.
Published: (2025)

Few-Shot and Training-Free Review Generation via Conversational Prompting
by: Kusano, Genki
Published: (2025)

Few-Shot Query Intent Detection via Relation-Aware Prompt Learning
by: Zhang, Liang, et al.
Published: (2025)

Exploiting Duality in Open Information Extraction with Predicate Prompt
by: Chen, Zhen, et al.
Published: (2024)

ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization
by: Mao, Chen, et al.
Published: (2024)