Image de couverture de livre

LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tamo, J. Ben, Carlander-Reuterfelt, Daniel, Rubin, Jonathan, Hong, Dezhi, Wang, Mingxian, Poliannikov, Oleg
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics
par: Liu, Zhu, et autres
Publié: (2024)

Positional Cognitive Specialization: Where Do LLMs Learn To Comprehend and Speak Your Language?
par: Salim, Luis Frentzen, et autres
Publié: (2026)

Mirror, Mirror on the Wall -- Which is the Best Model of Them All?
par: Sayed, Dina, et autres
Publié: (2025)

African Literacies: Which of Them Matter, and Why?
par: Parry, Kate
Publié: (2010)

BYOL: Bring Your Own Language Into LLMs
par: Zamir, Syed Waqas, et autres
Publié: (2026)

Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
par: Lipinski, Olaf, et autres
Publié: (2024)

How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them
par: Liao, Disen, et autres
Publié: (2026)

Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval
par: Rubin, Ohad, et autres
Publié: (2023)

How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
par: Zeng, Yi, et autres
Publié: (2024)

Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
par: Li, Ming, et autres
Publié: (2024)

Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference
par: Finkelshtein, Ben, et autres
Publié: (2025)

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
par: Shi, Zeru, et autres
Publié: (2026)

LLMs for Doctors: Leveraging Medical LLMs to Assist Doctors, Not Replace Them
par: Xie, Wenya, et autres
Publié: (2024)

How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data
par: Wang, Yejie, et autres
Publié: (2024)

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning
par: Zhang, Hongbin, et autres
Publié: (2024)

Conversations: Love Them, Hate Them, Steer Them
par: Chebrolu, Niranjan, et autres
Publié: (2025)

LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based Evaluation
par: Raval, Ananya, et autres
Publié: (2025)

Cash or Comfort? How LLMs Value Your Inconvenience
par: Cedro, Mateusz, et autres
Publié: (2025)

Divide-or-Conquer? Which Part Should You Distill Your LLM?
par: Wu, Zhuofeng, et autres
Publié: (2024)

Which Demographics do LLMs Default to During Annotation?
par: Schäfer, Johannes, et autres
Publié: (2024)

EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models
par: Tamo, J. Ben, et autres
Publié: (2026)

LLMs Can Plan Only If We Tell Them
par: Sel, Bilgehan, et autres
Publié: (2025)

Syntriever: How to Train Your Retriever with Synthetic Data from LLMs
par: Kim, Minsang, et autres
Publié: (2025)

Speaking the Same Language: Leveraging LLMs in Standardizing Clinical Data for AI
par: Sett, Arindam, et autres
Publié: (2024)

Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?
par: Bian, Ning, et autres
Publié: (2024)

Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
par: Zhao, Siyan, et autres
Publié: (2025)

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
par: Zhao, Weixiang, et autres
Publié: (2025)

Barriers to Universal Reasoning With Transformers (And How to Overcome Them)
par: Kraus, Oliver, et autres
Publié: (2026)

One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation
par: Siledar, Tejpalsingh, et autres
Publié: (2024)

Which Language Lab To Do What?
par: Plastre, Guy
Publié: (1968)

Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs
par: Li, Junyi Jessy, et autres
Publié: (2026)

Fine-Tune, Don't Prompt, Your Language Model to Identify Biased Language in Clinical Notes
par: Landi, Isotta, et autres
Publié: (2026)

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
par: Dang, John, et autres
Publié: (2024)

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From
par: Tong, Yao, et autres
Publié: (2025)

How Much of Your Data Can Suck? Thresholds for Domain Performance and Emergent Misalignment in LLMs
par: Ouyang, Jian, et autres
Publié: (2025)

StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control
par: Zhao, Haishu, et autres
Publié: (2026)

How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?
par: Doostmohammadi, Ehsan, et autres
Publié: (2024)

Teaching LLMs How to Learn with Contextual Fine-Tuning
par: Choi, Younwoo, et autres
Publié: (2025)

Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement
par: Tsai, Yu-Che, et autres
Publié: (2025)

Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca
par: Chen, Pinzhen, et autres
Publié: (2023)