Related papers: Model Merging and Safety Alignment: One Bad Model …

The advent of Large Language Models (LLMs) has garnered significant popularity and wielded immense power across various domains within Natural Language Processing (NLP). While their capabilities are undeniably impressive, it is crucial to…

Model merging is a promising lightweight model empowerment technique that does not rely on expensive computing devices (e.g., GPUs) or require the collection of specific training data. Instead, it involves editing different upstream model…

Large Language Models (LLMs) have shown high capabilities in several software development-related tasks such as program repair, documentation, code refactoring, debugging, and testing. However, training these models requires massive amount…

While LLMs excel at general tasks, they struggle in specialized domains like finance, requiring diverse skills in domain knowledge, mathematical reasoning, and multilingual processing. Merging domain-specific Continual Pre-training (CPT)…

With the evolution of large language models (LLMs), their robustness against individual simple biases has been enhanced. However, we observe that the ensemble of multiple simple biases still exerts a significant adverse impact on LLMs.…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Recent work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned. A survey of experts prior to publication revealed this was highly unexpected,…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains. These results prompted concerns about the emergence of harmful…

As Large Language Models (LLMs) excel across tasks and specialized domains, scaling LLMs based on existing models has garnered significant attention, which faces the challenge of decreasing performance when combining disparate models.…

Empowered by vast internal knowledge reservoir, the new generation of large language models (LLMs) demonstrate untapped potential to tackle medical tasks. However, there is insufficient effort made towards summoning up a synergic effect…

Endowing models with consistent multilingual performance can be achieved by mixing pre-training data, or post-training approaches such as language-specific model merging. In this work, we test whether merging can be applied to monolingually…

Achieving high-performing language models which include medium- and lower-resource languages remains a challenge. Massively multilingual models still underperform compared to language-specific adaptations, especially at smaller model…

The pre-trained language models are continually fine-tuned to better support downstream applications. However, this operation may result in significant performance degeneration on general tasks beyond the targeted domain. To overcome this…

Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs)…

Fine-tuning of Large Language Models (LLMs) has become the default practice for improving model performance on a given task. However, performance improvement comes at the cost of training on vast amounts of annotated data which could be…

Large language models (LLMs) have demonstrated remarkable capabilities across a broad spectrum of tasks. They have attracted significant attention and been deployed in numerous downstream applications. Nevertheless, akin to a double-edged…

Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT). However, this CT-then-SFT approach struggles with limited data in the context of low-resource…

Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in…