Related papers: Cross-Lingual Activation Steering for Multilingual…
Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effective, existing methods often apply a fixed steering strength to…
Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers…
Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is…
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…
Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the former is time-consuming and expensive, and the latter is not precisely controllable and often…
Recent work in activation steering has demonstrated the potential to better control the outputs of Large Language Models (LLMs), but it involves finding steering vectors. This is difficult because engineers do not typically know how…
If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset. To test this, we take multilingual in-context learning as a case study, where few-shot…
Activation steering has emerged as a promising alternative for controlling language-model behavior at inference time by modifying intermediate representations while keeping model parameters frozen. However, large-scale evaluations such as…
Cross-lingual alignment (CLA) aims to align multilingual representations, enabling Large Language Models (LLMs) to seamlessly transfer knowledge across languages. While intuitive, we hypothesize, this pursuit of representational convergence…
Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…
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…
Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…
Large language models demonstrate reasonable multilingual abilities, despite predominantly English-centric pretraining. However, the spontaneous multilingual alignment in these models is shown to be weak, leading to unsatisfactory…
The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…
Large language models (LLMs) often encode cognitive behaviors unpredictably across prompts, layers, and contexts, making them difficult to diagnose and control. We present CBMAS, a diagnostic framework for continuous activation steering,…
A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…
Multilinguality is crucial for extending recent advancements in language modelling to diverse linguistic communities. To maintain high performance while representing multiple languages, multilingual models ideally align representations,…
Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…
Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multilingual content into English-aligned representations at…
Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…