Related papers: Cross-Lingual Activation Steering for Multilingual…

The memorization of training data by Large Language Models (LLMs) poses significant risks, including privacy leaks and the regurgitation of copyrighted content. Activation steering, a technique that directly intervenes in model activations,…

Multilingual large language models (LLMs) achieve strong performance across languages, yet how language capabilities are organized at the neuron level remains poorly understood. Prior work has identified language-related neurons mainly…

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…

Robotic manipulation involves kinematic and semantic transitions that are inherently coupled via underlying actions. However, existing approaches plan within either semantic or latent space without explicitly aligning these cross-modal…

Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs.…

Cross-lingual text classification leverages text classifiers trained in a high-resource language to perform text classification in other languages with no or minimal fine-tuning (zero/few-shots cross-lingual transfer). Nowadays,…

Large language models are trained on massive scrapes of the web, as required by current scaling laws. Most progress is made for English, given its abundance of high-quality pretraining data. For most other languages, however, such high…

Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data…

Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to…

Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations,…

Despite their strong ability to retrieve knowledge in English, current large language models show imbalance abilities in different languages. Two approaches are proposed to address this, i.e., multilingual pretraining and multilingual…

Large Language Models (LLMs) have shown remarkable capabilities in natural language processing but exhibit significant performance gaps among different languages. Most existing approaches to address these disparities rely on pretraining or…

Scaling laws research has focused overwhelmingly on English -- yet the most prominent AI models explicitly serve billions of international users. In this work, we undertake the largest multilingual scaling laws study to date, totaling 774…

Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and…

Activation steering offers a promising approach to controlling the behavior of Large Language Models by directly manipulating their internal activations. However, most existing methods struggle to jointly steer multiple attributes, often…

Ensuring that Large Language Models (LLMs) generate text representative of diverse sub-populations is essential, particularly when key concepts related to under-represented groups are scarce in the training data. We address this challenge…

Without any explicit cross-lingual training data, multilingual language models can achieve cross-lingual transfer. One common way to improve this transfer is to perform realignment steps before fine-tuning, i.e., to train the model to build…

Large Language Models (LLMs) increasingly shape global discourse, making fairness and ideological neutrality essential for responsible AI deployment. Despite growing attention to political bias in LLMs, prior work largely focuses on…

Large vision-language models (LVLMs) have demonstrated exceptional capabilities in understanding visual information with human languages but also exhibit an imbalance in multilingual capabilities. In this work, we delve into the…