When large language models are aligned via supervised fine-tuning, they may encounter
new factual information that was not acquired through pre-training. It is often conjectured that …

Performance of large language models (LLMs) may vary with different prompts or
instructions of even the same task. One commonly recognized factor for this phenomenon is …

While Large language models (LLMs) have demonstrated considerable capabilities across
various natural language tasks, they often fall short of the performance achieved by domain …

Language models have shown impressive in-context-learning capabilities, which allow them
to benefit from input prompts and perform better on downstream end tasks. Existing works …

Retrieval Augmented Generation (RAG) improves large language models (LMs) by
incorporating non-parametric knowledge through evidence retrieval from external sources …

During the pretraining phase, large language models (LLMs) acquire vast amounts of
knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and …

While large language models (LLMs) showcase unprecedented capabilities, they also
exhibit certain inherent limitations when facing seemingly trivial tasks. A prime example is …

Abstract Information extraction (IE) of unstructured electronic health records is challenging
due to the semantic complexity of textual data. Generative large language models (LLMs) …

Different entities with the same name can be difficult to distinguish. Handling confusing entity
mentions is a crucial skill for language models (LMs). For example, given the question" …

Multi-label classification of unstructured electronic health records (EHR) poses challenges
due to the inherent semantic complexity in textual data. Advances in natural language …