Cover Image

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sundar, Anirudh, Williamson, Sinead, Metcalf, Katherine, Theobald, Barry-John, Seto, Skyler, Fedzechkina, Masha
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ExpertLens: Activation steering features are highly interpretable
by: Fedzechkina, Masha, et al.
Published: (2025)

Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter
by: Blaschke, Verena, et al.
Published: (2025)

Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks
by: de Seyssel, Maureen, et al.
Published: (2025)

What do your logits know? (The answer may surprise you!)
by: Fedzechkina, Masha, et al.
Published: (2026)

DSO: Direct Steering Optimization for Bias Mitigation
by: Paes, Lucas Monteiro, et al.
Published: (2025)

On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
by: Lin, Yong, et al.
Published: (2024)

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

LLMs are not (consistently) Bayesian: Quantifying internal (in)consistencies of LLMs' probabilistic beliefs
by: Chen, Chacha, et al.
Published: (2026)

Learning Spatially-Aware Language and Audio Embeddings
by: Devnani, Bhavika, et al.
Published: (2024)

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

Analyzing the Evaluation of Cross-Lingual Knowledge Transfer in Multilingual Language Models
by: Rajaee, Sara, et al.
Published: (2024)

Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions
by: Sedova, Anastasiia, et al.
Published: (2026)

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
by: Huang, Chen, et al.
Published: (2025)

Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention
by: Wang, Weixuan, et al.
Published: (2024)

Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards
by: Metcalf, Katherine, et al.
Published: (2024)

Theoretical Limits of Language Model Alignment
by: Paes, Lucas Monteiro, et al.
Published: (2026)

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

Evaluating Cross-Lingual Unlearning in Multilingual Language Models
by: Lizzo, Tyler, et al.
Published: (2026)

Aligning LLMs by Predicting Preferences from User Writing Samples
by: Aroca-Ouellette, Stéphane, et al.
Published: (2025)

PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories
by: Aroca-Ouellette, Stephane, et al.
Published: (2024)

Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models
by: Xu, Zixiang, et al.
Published: (2025)

LANGALIGN: Enhancing Non-English Language Models via Cross-Lingual Embedding Alignment
by: Kim, Jong Myoung, et al.
Published: (2025)

CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention
by: Ye, Zekai, et al.
Published: (2025)

Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models
by: Qi, Jirui, et al.
Published: (2023)

Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models
by: Choi, Minseok, et al.
Published: (2024)

Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?
by: Ai, Xi, et al.
Published: (2025)

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

SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning
by: Wang, Bin, et al.
Published: (2023)

Examining Multilingual Embedding Models Cross-Lingually Through LLM-Generated Adversarial Examples
by: Michail, Andrianos, et al.
Published: (2025)

An Efficient Approach for Studying Cross-Lingual Transfer in Multilingual Language Models
by: Faisal, Fahim, et al.
Published: (2024)

Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment
by: Yang, Wen, et al.
Published: (2025)

Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling
by: Grangier, David, et al.
Published: (2024)

Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks
by: Babakhin, Yauhen, et al.
Published: (2025)

Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution
by: Khan, Falaah Arif, et al.
Published: (2025)

Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
by: Aldeneh, Zakaria, et al.
Published: (2024)

Cross-Spectral Body Recognition with Side Information Embedding: Benchmarks on LLCM and Analyzing Range-Induced Occlusions on IJB-MDF
by: Nanduri, Anirudh, et al.
Published: (2025)

M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models
by: Maheshwary, Rishabh, et al.
Published: (2024)

Which Data Matter? Embedding-Based Data Selection for Speech Recognition
by: Aldeneh, Zakaria, et al.
Published: (2026)

Assessing the Role of Data Quality in Training Bilingual Language Models
by: Seto, Skyler, et al.
Published: (2025)

PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment
by: Li, Jiahuan, et al.
Published: (2024)