Imagen de Portada

CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gurgurov, Daniil, Ghussin, Yusser Al, Baeumel, Tanja, Chou, Cheng-Ting, Schramowski, Patrick, Mosbach, Marius, van Genabith, Josef, Ostermann, Simon
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
por: Ghussin, Yusser Al, et al.
Publicado: (2026)

Modular Arithmetic: Language Models Solve Math Digit by Digit
por: Baeumel, Tanja, et al.
Publicado: (2025)

Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation
por: Gurgurov, Daniil, et al.
Publicado: (2025)

DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge
por: Ghussin, Yusser Al, et al.
Publicado: (2026)

Sparse Subnetwork Enhancement for Underrepresented Languages in Large Language Models
por: Gurgurov, Daniil, et al.
Publicado: (2025)

Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms
por: Baeumel, Tanja, et al.
Publicado: (2026)

The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs
por: Baeumel, Tanja, et al.
Publicado: (2025)

On Multilingual Encoder Language Model Compression for Low-Resource Languages
por: Gurgurov, Daniil, et al.
Publicado: (2025)

Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages
por: Gurgurov, Daniil, et al.
Publicado: (2025)

Multilingual Political Views of Large Language Models: Identification and Steering
por: Gurgurov, Daniil, et al.
Publicado: (2025)

From Weights to Activations: Is Steering the Next Frontier of Adaptation?
por: Ostermann, Simon, et al.
Publicado: (2026)

The Latin Substrate: How Language Models Represent and Mediate Script Choice
por: Gurgurov, Daniil, et al.
Publicado: (2026)

ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance
por: Gurgurov, Daniil, et al.
Publicado: (2026)

GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge
por: Gurgurov, Daniil, et al.
Publicado: (2024)

Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters
por: Gurgurov, Daniil, et al.
Publicado: (2024)

Probing Context Localization of Polysemous Words in Pre-trained Language Model Sub-Layers
por: Vijayakumar, Soniya, et al.
Publicado: (2024)

Multilingual Large Language Models and Curse of Multilinguality
por: Gurgurov, Daniil, et al.
Publicado: (2024)

DualFact+: A Multimodal Fact Verification Framework for Procedural Video Understanding
por: Oguz, Cennet, et al.
Publicado: (2026)

Image-to-LaTeX Converter for Mathematical Formulas and Text
por: Gurgurov, Daniil, et al.
Publicado: (2024)

AutoPsyC: Automatic Recognition of Psychodynamic Conflicts from Semi-structured Interviews with Large Language Models
por: Hossain, Sayed Muddashir, et al.
Publicado: (2025)

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
por: Ostermann, Simon, et al.
Publicado: (2024)

Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
por: Shi, Dan, et al.
Publicado: (2026)

Benchmarking Cross-Lingual Semantic Alignment in Multilingual Embeddings
por: Gong, Wen G.
Publicado: (2025)

Lessing divers. Soziale Milieus, Genderformationen, Ethnien und Religionen By DirkNiefanger, Wallstein. 2023. pp. 395. € 34,00 (hardcover or ebook)
por: Martin Baeumel
Publicado: (2024)

Cross-Lingual Activation Steering for Multilingual Language Models
por: Pokharel, Rhitabrat, et al.
Publicado: (2026)

CLaP -- State Detection from Time Series
por: Ermshaus, Arik, et al.
Publicado: (2025)

What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations
por: Trinley, Katharina, et al.
Publicado: (2025)

Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution
por: Anikina, Tatiana, et al.
Publicado: (2025)

Not All Data Are Unlearned Equally
por: Krishnan, Aravind, et al.
Publicado: (2025)

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
por: Sundar, Anirudh, et al.
Publicado: (2025)

SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs
por: Härle, Ruben, et al.
Publicado: (2024)

When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation
por: Tan, David, et al.
Publicado: (2026)

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

Operationalising the Superficial Alignment Hypothesis via Task Complexity
por: Vergara-Browne, Tomás, et al.
Publicado: (2026)

Understanding Cross-Lingual Alignment -- A Survey
por: Hämmerl, Katharina, et al.
Publicado: (2024)

Beyond Overcorrection: Evaluating Diversity in T2I Models with DivBench
por: Friedrich, Felix, et al.
Publicado: (2025)

The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
por: Rizvi-Martel, Michael, et al.
Publicado: (2026)

CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics
por: Jeong, Andrew, et al.
Publicado: (2026)

Pralekha: Cross-Lingual Document Alignment for Indic Languages
por: Suryanarayanan, Sanjay, et al.
Publicado: (2024)

mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?
por: Hua, Tianze, et al.
Publicado: (2024)