Imagen de Portada

STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Jiaqian, Hu, Qisheng, Li, Jing, Wang, Wenya
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?
por: Hu, Qisheng, et al.
Publicado: (2024)

Towards Generalizable Implicit In-Context Learning with Attention Routing
por: Li, Jiaqian, et al.
Publicado: (2025)

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
por: Li, Jiaqian, et al.
Publicado: (2026)

UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation
por: Gao, Jun, et al.
Publicado: (2024)

Soft Head Selection for Injecting ICL-Derived Task Embeddings
por: Park, Jungwon, et al.
Publicado: (2025)

C-ICL: Contrastive In-context Learning for Information Extraction
por: Mo, Ying, et al.
Publicado: (2024)

ParaICL: Towards Parallel In-Context Learning
por: Li, Xingxuan, et al.
Publicado: (2024)

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
por: Mishra, Aayush, et al.
Publicado: (2025)

Refract ICL: Rethinking Example Selection in the Era of Million-Token Models
por: Akula, Arjun R., et al.
Publicado: (2025)

Inference-time Alignment via Sparse Junction Steering
por: Hu, Runyi, et al.
Publicado: (2026)

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
por: Li, Hao, et al.
Publicado: (2026)

Multi-objective Large Language Model Alignment with Hierarchical Experts
por: Li, Zhuo, et al.
Publicado: (2025)

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

CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
por: Wang, Xintong, et al.
Publicado: (2024)

Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
por: Wu, Zhaoxuan, et al.
Publicado: (2024)

Bridging Sequence-Structure Alignment in RNA Foundation Models
por: Yang, Heng, et al.
Publicado: (2024)

TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection
por: Liu, Hui, et al.
Publicado: (2024)

Task Diversity Shortens the ICL Plateau
por: Kim, Jaeyeon, et al.
Publicado: (2024)

HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction
por: Liu, Shuliang, et al.
Publicado: (2022)

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars
por: Hua, Yuncheng, et al.
Publicado: (2025)

Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries
por: Wu, Yin, et al.
Publicado: (2025)

MAATS: A Multi-Agent Automated Translation System Based on MQM Evaluation
por: Wang, George, et al.
Publicado: (2025)

On the Limitations of Steering in Language Model Alignment
por: Niranjan, Chebrolu, et al.
Publicado: (2025)

BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection
por: Hu, Zhengpei, et al.
Publicado: (2026)

Training Language Models to Generate Text with Citations via Fine-grained Rewards
por: Huang, Chengyu, et al.
Publicado: (2024)

Structured Episodic Event Memory
por: Lu, Zhengxuan, et al.
Publicado: (2026)

Interpretable Multimodal Misinformation Detection with Logic Reasoning
por: Liu, Hui, et al.
Publicado: (2023)

Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
por: Li, Tung-Ling, et al.
Publicado: (2025)

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

CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark
por: Gurgurov, Daniil, et al.
Publicado: (2026)

MateICL: Mitigating Attention Dispersion in Large-Scale In-Context Learning
por: Ahmed, Murtadha, et al.
Publicado: (2025)

ICL CIPHERS: Quantifying "Learning" in In-Context Learning via Substitution Ciphers
por: Fang, Zhouxiang, et al.
Publicado: (2025)

MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems
por: Li, Kaixin, et al.
Publicado: (2024)

Vector-ICL: In-context Learning with Continuous Vector Representations
por: Zhuang, Yufan, et al.
Publicado: (2024)

Masked Structural Growth for 2x Faster Language Model Pre-training
por: Yao, Yiqun, et al.
Publicado: (2023)

Can Language Models Act as Knowledge Bases at Scale?
por: He, Qiyuan, et al.
Publicado: (2024)

Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance
por: Qorib, Muhammad Reza, et al.
Publicado: (2024)

CrossICL: Cross-Task In-Context Learning via Unsupervised Demonstration Transfer
por: Gao, Jinglong, et al.
Publicado: (2025)

Fine-Grained Activation Steering: Steering Less, Achieving More
por: Feng, Zijian, et al.
Publicado: (2026)

Generative Deduplication For Socia Media Data Selection
por: Li, Xianming, et al.
Publicado: (2024)