Image de couverture de livre

ExpertSteer: Intervening in LLMs through Expert Knowledge

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Weixuan, Wu, Minghao, Haddow, Barry, Birch, Alexandra
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Demystifying Multilingual Chain-of-Thought in Process Reward Modeling
par: Wang, Weixuan, et autres
Publié: (2025)

HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models
par: Wang, Weixuan, et autres
Publié: (2025)

Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization
par: Wang, Weixuan, et autres
Publié: (2025)

Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention
par: Wang, Weixuan, et autres
Publié: (2024)

Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs
par: Wang, Weixuan, et autres
Publié: (2024)

Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task
par: Ranaldi, Leonardo, et autres
Publié: (2025)

MGen: Millions of Naturally Occurring Generics in Context
par: Cilleruelo, Gustavo, et autres
Publié: (2025)

When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale
par: Baziotis, Christos, et autres
Publié: (2023)

The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics
par: Bogoychev, Nikolay, et autres
Publié: (2023)

Compact Speech Translation Models via Discrete Speech Units Pretraining
par: Lam, Tsz Kin, et autres
Publié: (2024)

Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations
par: Ranaldi, Leonardo, et autres
Publié: (2025)

Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translation
par: Shen, Sherrie, et autres
Publié: (2025)

The Prosody of Emojis
par: Zhou, Giulio, et autres
Publié: (2025)

Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases
par: Zhou, Giulio, et autres
Publié: (2024)

Generics are puzzling. Can language models find the missing piece?
par: Calderón, Gustavo Cilleruelo, et autres
Publié: (2024)

Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steering
par: Chen, Yuxin, et autres
Publié: (2026)

Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs
par: Bai, Jun, et autres
Publié: (2025)

Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translation
par: Iyer, Vivek, et autres
Publié: (2024)

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
par: Wang, Weixuan, et autres
Publié: (2024)

Steering MoE LLMs via Expert (De)Activation
par: Fayyaz, Mohsen, et autres
Publié: (2025)

From Beginner to Expert: Modeling Medical Knowledge into General LLMs
par: Li, Qiang, et autres
Publié: (2023)

Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation
par: Klimaszewski, Mateusz, et autres
Publié: (2024)

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
par: Chai, Ziwei, et autres
Publié: (2024)

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs
par: Zhou, Yixiao, et autres
Publié: (2025)

Integrating Expert Knowledge into Logical Programs via LLMs
par: Górski, Franciszek, et autres
Publié: (2025)

Context and System Fusion in Post-ASR Emotion Recognition with Large Language Models
par: Stepachev, Pavel, et autres
Publié: (2024)

Mixture of Experts for Low-Resource LLMs
par: Joseph, Ori Bar, et autres
Publié: (2026)

LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models
par: Yang, Jingyuan, et autres
Publié: (2025)

DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
par: Bai, Sikai, et autres
Publié: (2025)

Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
par: Zhang, Zeliang, et autres
Publié: (2024)

Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models
par: Wang, Yilin, et autres
Publié: (2025)

SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
par: Zhuang, Haomin, et autres
Publié: (2024)

Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
par: Bandarkar, Lucas, et autres
Publié: (2026)

Test-Time Steering for Lossless Text Compression via Weighted Product of Experts
par: Zhang, Qihang, et autres
Publié: (2025)

dMoE: dLLMs with Learnable Block Experts
par: Feng, Sicheng, et autres
Publié: (2026)

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
par: Sukhbaatar, Sainbayar, et autres
Publié: (2024)

Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?
par: Chen, Pinzhen, et autres
Publié: (2024)

Iterative Translation Refinement with Large Language Models
par: Chen, Pinzhen, et autres
Publié: (2023)

An Expert-grounded benchmark of General Purpose LLMs in LCA
par: Donaldson, Artur, et autres
Publié: (2025)

CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts
par: Su, Zhenpeng, et autres
Publié: (2024)