相关论文: Neural FOXP2 -- Language Specific Neuron Steering …

Language-specific neurons in LLMs that strongly correlate with individual languages have been shown to influence model behavior by deactivating them. However, their role in amplification remains underexplored. This work investigates the…

Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…

Current decoder-based pre-trained language models (PLMs) successfully demonstrate multilingual capabilities. However, it is unclear how these models handle multilingualism. We analyze the neuron-level internal behavior of multilingual…

Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant languages. Prior work attributes this gap to imbalances between shared and language-specific neurons…

Multilingual large language models (LLMs) aim towards robust natural language understanding across diverse languages, yet their performance significantly degrades on low-resource languages. This work explores whether existing techniques to…

This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify…

As large language models (LLMs) advance in their linguistic capacity, understanding how they capture aspects of language competence remains a significant challenge. This study therefore employs psycholinguistic paradigms in English, which…

Deterministically controlling the target generation language of large multilingual language models (LLMs) remains a fundamental challenge, particularly in zero-shot settings where neither explicit language prompts nor fine-tuning are…

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged…

Large language models (LLMs) exhibit strong multilingual abilities, yet the neural mechanisms behind language-specific processing remain unclear. We analyze language-specific neurons in Llama-3.1-8B, Mistral-Nemo-12B, and Aya-Expanse-8B &…

Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear directions in activation space that can be manipulated at…

Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. The major challenges are catastrophic forgetting and parameter interference for finetuning…

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…

Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal,…

Commanding a robot to navigate with natural language instructions is a long-term goal for grounded language understanding and robotics. But the dominant language is English, according to previous studies on vision-language navigation (VLN).…

Despite advances in multilingual capabilities, most large language models (LLMs) remain English-centric in their training and, crucially, in their production of reasoning traces. Even when tasked with non-English problems, these models…

We ask whether multilingual language models trained on unbalanced, English-dominated corpora use English as an internal pivot language -- a question of key importance for understanding how language models function and the origins of…

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. It remains a challenging problem to explain the underlying mechanisms by which LLMs…

Multilingual Alignment is an effective and representative paradigm to enhance LLMs' multilingual capabilities, which transfers the capabilities from the high-resource languages to the low-resource languages. Meanwhile, some research on…