Imagen de Portada

On Relation-Specific Neurons in Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Yihong, Chen, Runsheng, Hirlimann, Lea, Hakimi, Ahmad Dawar, Wang, Mingyang, Kargaran, Amir Hossein, Rothe, Sascha, Yvon, François, Schütze, Hinrich
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

How Programming Concepts and Neurons Are Shared in Code Language Models
por: Kargaran, Amir Hossein, et al.
Publicado: (2025)

Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learning for Hostility Detection
por: Hakimi, Ahmad Dawar, et al.
Publicado: (2026)

MaskLID: Code-Switching Language Identification through Iterative Masking
por: Kargaran, Amir Hossein, et al.
Publicado: (2024)

GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
por: Kargaran, Amir Hossein, et al.
Publicado: (2024)

GlotScript: A Resource and Tool for Low Resource Writing System Identification
por: Kargaran, Amir Hossein, et al.
Publicado: (2023)

GlotLID: Language Identification for Low-Resource Languages
por: Kargaran, Amir Hossein, et al.
Publicado: (2023)

Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models
por: Hakimi, Ahmad Dawar, et al.
Publicado: (2025)

GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts
por: Kargaran, Amir Hossein, et al.
Publicado: (2026)

Tracing Multilingual Factual Knowledge Acquisition in Pretraining
por: Liu, Yihong, et al.
Publicado: (2025)

On the Entity-Level Alignment in Crosslingual Consistency
por: Liu, Yihong, et al.
Publicado: (2025)

MenuCraft: Interactive Menu System Design with Large Language Models
por: Kargaran, Amir Hossein, et al.
Publicado: (2023)

How Transliterations Improve Crosslingual Alignment
por: Liu, Yihong, et al.
Publicado: (2024)

SLAyiNG: Towards Queer Language Processing
por: Veloso, Leonor, et al.
Publicado: (2025)

MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment
por: Kargaran, Amir Hossein, et al.
Publicado: (2024)

Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchu
por: Pei, Renhao, et al.
Publicado: (2025)

BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
por: Mondorf, Philipp, et al.
Publicado: (2025)

Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models
por: Liu, Yihong, et al.
Publicado: (2026)

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining
por: Liu, Yihong, et al.
Publicado: (2023)

GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models
por: Gerstner, Sebastian, et al.
Publicado: (2026)

Relational Linearity is a Predictor of Hallucinations
por: Lu, Yuetian, et al.
Publicado: (2026)

Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment
por: Xhelili, Orgest, et al.
Publicado: (2024)

LangSAMP: Language-Script Aware Multilingual Pretraining
por: Liu, Yihong, et al.
Publicado: (2024)

Refusal Direction is Universal Across Safety-Aligned Languages
por: Wang, Xinpeng, et al.
Publicado: (2025)

Robustness Testing of Multi-Modal Models in Varied Home Environments for Assistive Robots
por: Hirlimann, Lea, et al.
Publicado: (2024)

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding
por: Feng, Qi, et al.
Publicado: (2025)

Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners
por: Liu, Yihong, et al.
Publicado: (2026)

TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models
por: Liu, Yihong, et al.
Publicado: (2024)

Understanding Gated Neurons in Transformers from Their Input-Output Functionality
por: Gerstner, Sebastian, et al.
Publicado: (2025)

Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors
por: Zhao, Raoyuan, et al.
Publicado: (2025)

HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization
por: Özeren, Enes, et al.
Publicado: (2025)

TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data
por: Liu, Yihong, et al.
Publicado: (2024)

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
por: Wang, Mingyang, et al.
Publicado: (2025)

Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders
por: Veitsman, Yana, et al.
Publicado: (2026)

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
por: Nie, Ercong, et al.
Publicado: (2025)

The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing
por: Cao, Yuan, et al.
Publicado: (2026)

Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts
por: Ma, Chunlan, et al.
Publicado: (2024)

A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
por: Zhao, Raoyuan, et al.
Publicado: (2025)

GIRT-Model: Automated Generation of Issue Report Templates
por: Nikeghbal, Nafiseh, et al.
Publicado: (2024)

MoSECroT: Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer
por: Ye, Haotian, et al.
Publicado: (2024)

Enhancing Robustness of Autoregressive Language Models against Orthographic Attacks via Pixel-based Approach
por: Yang, Han, et al.
Publicado: (2025)