Related papers: DART: Mitigating Harm Drift in Difference-Aware LL…
Large language models (LLMs) are increasingly deployed worldwide, yet their safety alignment remains predominantly English-centric. This allows for vulnerabilities in non-English contexts, especially with low-resource languages. We…
Large Language Models have demonstrated superior performance across a wide range of tasks, but they still exhibit undesirable errors due to incorrect knowledge learned from the training data. To avoid this, knowledge editing methods emerged…
The rapid rise of large language model (LLM)-based tutors in K--12 education has fostered a misconception that generative models can replace traditional learner modelling for adaptive instruction. This is especially problematic in K--12…
Large Language Models (LLMs) have demonstrated promising reasoning capabilities in robotics; however, their application in multi-robot systems remains limited, particularly in handling task dependencies. This paper introduces DART-LLM, a…
Large Language Models (LLMs) have great potential in the field of health care, yet they face great challenges in adapting to rapidly evolving medical knowledge. This can lead to outdated or contradictory treatment suggestions. This study…
Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when the retrieved…
The rise of pre-trained language models has yielded substantial progress in the vast majority of Natural Language Processing (NLP) tasks. However, a generic approach towards the pre-training procedure can naturally be sub-optimal in some…
Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…
Fine-tuning large language models (LLMs) can lead to unintended out-of-distribution generalization. Standard approaches to this problem rely on modifying training data, for example by adding data that better specify the intended…
In recent years, Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations? A popular concept, referred to as self-refinement, postulates that LLMs can detect and…
Financial institutions deploy Large Language Models (LLMs) for reconciliations, regulatory reporting, and client communications, but nondeterministic outputs (output drift) undermine auditability and trust. We quantify drift across five…
Not a day goes by without hearing about the impressive feats of large language models (LLMs), and equally, not a day passes without hearing about their challenges. LLMs are notoriously vulnerable to biases in their dataset, leading to…
Large language models (LLMs) have demonstrated revolutionary capabilities in understanding complex contexts and performing a wide range of tasks. However, LLMs can also answer questions that are unethical or harmful, raising concerns about…
Pretraining Large Language Models (LLMs) on large corpora of textual data is now a standard paradigm. When using these LLMs for many downstream applications, it is common to additionally bake in new knowledge (e.g., time-critical news, or…
Safety alignment in Large Language Models (LLMs) inherently presents a multi-objective optimization conflict, often accompanied by an unintended degradation of general capabilities. Existing mitigation strategies typically rely on global…
The automatic generation of radiology reports has emerged as a promising solution to reduce a time-consuming task and accurately capture critical disease-relevant findings in X-ray images. Previous approaches for radiology report generation…
LLMs are commonly used in retrieval-augmented applications to execute user instructions based on data from external sources. For example, modern search engines use LLMs to answer queries based on relevant search results; email plugins…
Despite the strong performance of Large Language Models (LLMs) on complex instruction-following tasks, precise control of output length remains a persistent challenge. Existing methods primarily attempt to enforce length constraints by…
Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters…
LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…