English
Related papers

Related papers: Cross-Lingual Activation Steering for Multilingual…

200 papers

The emergent cross-lingual transfer seen in multilingual pretrained models has sparked significant interest in studying their behavior. However, because these analyses have focused on fully trained multilingual models, little is known about…

Computation and Language · Computer Science 2022-10-25 Terra Blevins , Hila Gonen , Luke Zettlemoyer

Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a…

Cryptography and Security · Computer Science 2025-11-24 Zhiyuan Xu , Stanislav Abaimov , Joseph Gardiner , Sana Belguith

The language ability of Large Language Models (LLMs) is often unbalanced towards English because of the imbalance in the distribution of the pre-training data. This disparity is demanded in further fine-tuning and affecting the…

Computation and Language · Computer Science 2024-10-30 Leonardo Ranaldi , Giulia Pucci , Andre Freitas

English pretrained language models, which make up the backbone of many modern NLP systems, require huge amounts of unlabeled training data. These models are generally presented as being trained only on English text but have been found to…

Computation and Language · Computer Science 2022-11-18 Terra Blevins , Luke Zettlemoyer

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Cryptography and Security · Computer Science 2026-02-06 Chen Xiong , Zhiyuan He , Pin-Yu Chen , Ching-Yun Ko , Tsung-Yi Ho

Large language models (LLMs) have multilingual capabilities and can solve tasks across various languages. However, we show that current LLMs make key decisions in a representation space closest to English, regardless of their input and…

Computation and Language · Computer Science 2025-02-24 Lisa Schut , Yarin Gal , Sebastian Farquhar

Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important -- especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept…

Computation and Language · Computer Science 2026-02-02 Felicia Körner , Max Müller-Eberstein , Anna Korhonen , Barbara Plank

The capacity and effectiveness of pre-trained multilingual models (MLMs) for zero-shot cross-lingual transfer is well established. However, phenomena of positive or negative transfer, and the effect of language choice still need to be fully…

Computation and Language · Computer Science 2024-04-01 Fahim Faisal , Antonios Anastasopoulos

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

Machine Learning · Computer Science 2026-02-04 Magamed Taimeskhanov , Samuel Vaiter , Damien Garreau

Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), but SAE-based language control remains unreliable in multilingual settings: most SAEs are trained on…

Computation and Language · Computer Science 2026-05-25 Yusser Al Ghussin , Daniil Gurgurov , Tanja Baeumel , Josef van Genabith , Patrick Schramowski , Simon Ostermann

Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models. In this work, we found that the cross-lingual alignment can be further improved by training seq2seq models on sentence pairs…

Computation and Language · Computer Science 2020-10-28 Chau Tran , Yuqing Tang , Xian Li , Jiatao Gu

Despite their remarkable ability to capture linguistic nuances across diverse languages, questions persist regarding the degree of alignment between languages in multilingual embeddings. Drawing inspiration from research on high-dimensional…

Computation and Language · Computer Science 2024-05-24 Basel Mousi , Nadir Durrani , Fahim Dalvi , Majd Hawasly , Ahmed Abdelali

Current large language models (LLMs) often exhibit imbalances in multilingual capabilities and cultural adaptability, largely attributed to their English-centric pre-training data. In this paper, we introduce and investigate cross-lingual…

Computation and Language · Computer Science 2026-04-13 Yangfan Ye , Xiaocheng Feng , Xiachong Feng , Libo Qin , Yichong Huang , Lei Huang , Weitao Ma , Qichen Hong , Zhirui Zhang , Yunfei Lu , Xiaohui Yan , Duyu Tang , Dandan Tu , Bing Qin

Multimodal large language models can exhibit text dominance, over-relying on linguistic priors instead of grounding predictions in non-text inputs. One example is large audio-language models (LALMs) where decisive audio evidence can be…

Sound · Computer Science 2026-03-10 Neta Glazer , Lenny Aharon , Ethan Fetaya

Contextual-LAS (CLAS) has been shown effective in improving Automatic Speech Recognition (ASR) of rare words. It relies on phrase-level contextual modeling and attention-based relevance scoring without explicit contextual constraint which…

Computation and Language · Computer Science 2024-12-20 Mengzhi Wang , Shifu Xiong , Genshun Wan , Hang Chen , Jianqing Gao , Lirong Dai

Shared multilingual representations are essential for cross-lingual tasks and knowledge transfer across languages. This study looks at the impact of parallel data, i.e. translated sentences, in pretraining as a signal to trigger…

Computation and Language · Computer Science 2026-04-01 Julius Leino , Jörg Tiedemann

Object hallucination remains a primary obstacle to the reliable deployment of Multimodal Large Language Models (MLLMs). Current inference-time mitigation methods mainly assume hallucinations stem from visual neglect, steering models to…

Computation and Language · Computer Science 2026-05-28 Jingwen Wu , Xijun Zhang , Ge Song

The current Large Language Models (LLMs) face significant challenges in improving their performance on low-resource languages and urgently need data-efficient methods without costly fine-tuning. From the perspective of language-bridge, we…

Computation and Language · Computer Science 2025-09-24 Yuemei Xu , Kexin Xu , Jian Zhou , Ling Hu , Lin Gui

As large language models (LLMs) evolve in complexity and capability, the efficacy of less widely deployed alignment techniques are uncertain. Building on previous work on activation steering and contrastive activation addition (CAA), this…

Machine Learning · Computer Science 2025-07-17 Sheikh Abdur Raheem Ali , Justin Xu , Ivory Yang , Jasmine Xinze Li , Ayse Arslan , Clark Benham

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Computation and Language · Computer Science 2025-09-29 Zheng Wei Lim , Alham Fikri Aji , Trevor Cohn