HICL: Hashtag-Driven In-Context Learning for Social Media Natural Language Understanding.

Natural language understanding (NLU) is integral to various social media applications. However, the existing NLU models rely heavily on context for semantic learning, resulting in compromised performance when faced with short and noisy social media content. To address this issue, we leverage in-context learning (ICL), wherein language models learn to make inferences by conditioning on a handful of demonstrations to enrich the context and propose a novel hashtag-driven ICL (HICL) framework. Concretely, we pretrain a model, which employs #hashtags (user-annotated topic labels) to drive BERT-based pretraining through contrastive learning. Our objective here is to enable to gain the ability to incorporate topic-related semantic information, which allows it to retrieve topic-related posts to enrich contexts and enhance social media NLU with noisy contexts. To further integrate the retrieved context with the source text, we employ a gradient-based method to identify trigger terms useful in fusing information from both sources. For empirical studies, we collected 45 M tweets to set up an in-context NLU benchmark, and the experimental results on seven downstream tasks show that HICL substantially advances the previous state-of-the-art results. Furthermore, we conducted an extensive analysis and found that the following hold: 1) combining source input with a top-retrieved post from is more effective than using semantically similar posts and 2) trigger words can largely benefit in merging context from the source and retrieved posts.

The role of Chinese herbal medicine in the treatment of diabetic nephropathy by regulating endoplasmic reticulum stress.

Diabetic nephropathy (DN), a prevalent microvascular complication of diabetes mellitus, is the primary contributor to end-stage renal disease in developed countries. Existing clinical interventions for DN encompass lifestyle modifications, blood glucose regulation, blood pressure reduction, lipid management, and avoidance of nephrotoxic medications. Despite these measures, a significant number of patients progress to end-stage renal disease, underscoring the need for additional therapeutic strategies. The endoplasmic reticulum (ER) stress response, a cellular defense mechanism in eukaryotic cells, has been implicated in DN pathogenesis. Moderate ER stress can enhance cell survival, whereas severe or prolonged ER stress may trigger apoptosis. As such, the role of ER stress in DN presents a potential avenue for therapeutic modulation. Chinese herbal medicine, a staple in Chinese healthcare, has emerged as a promising intervention for DN. Existing research suggests that some herbal remedies may confer renoprotective benefits through the modulation of ER stress. This review explores the involvement of ER stress in the pathogenesis of DN and the advancements in Chinese herbal medicine for ER stress regulation, aiming to inspire new clinical strategies for the prevention and management of DN.