Large Language Models (LLMs) have shown strong performance in tasks such as zero- and few-shot information extraction from clinical text without domain-specific training. However, in the ICD coding task, LLMs often hallucinate key details and produce high-recall but low-precision outputs due to the high-dimensional and imbalanced nature of ICD code distributions. Existing LLM-based approaches typically fail to capture the complex, dynamic interactions among human agents involved in real-world coding workflows-such as patients, physicians, and coders-and often lack interpretability and reliability. To address these challenges, we propose a novel multi-agent framework for ICD coding that simulates the real-world process using five role-specific LLM agents-patient, physician, coder, reviewer, and adjuster-and integrates the Subjective, Objective, Assessment, and Plan (SOAP) structure from Electronic Health Records to enhance performance. Evaluated on the MIMIC-III dataset, our method significantly outperforms zero-shot Chain-of-Thought prompting, self-consistency strategies, and LLM-designed agent baselines, particularly for rare codes. Ablation studies confirm the contribution of each agent role, and the system achieves competitive performance with state-of-the-art fine-tuned models, while offering better explainability and requiring no task-specific pre-training.

Large language models (LLMs) have shown remarkable abilities in generating natural texts for various tasks across different domains. However, applying LLMs to clinical settings still poses significant challenges, as it requires specialized knowledge, vocabulary, as well as reliability. In this work, we propose a novel method of instruction fine-tuning for adapting LLMs to the clinical domain, which leverages the instruction-following capabilities of LLMs and the availability of diverse real-world data sources. We generate instructions, inputs, and outputs covering a wide spectrum of clinical services, from primary cares to nursing, radiology, physician, and social work, and use them to fine-tune LLMs. We evaluated the fine-tuned LLM, LlamaCare, on various clinical tasks, such as generating discharge summaries, predicting mortality and length of stay, and more. Using both automatic and human metrics, we demonstrated that LlamaCare surpasses other LLM baselines in predicting clinical outcomes and producing more accurate and coherent clinical texts. We also discuss the challenges and limitations of LLMs that need to be addressed before they can be widely adopted in clinical settings.

Neural machine translation (NMT) models have achieved state-of-the-art translation quality with a large quantity of parallel corpora available. However, their performance suffers significantly when it comes to domain-specific translations, in which training data are usually scarce. In this paper, we present a novel NMT model with a new word embedding transition technique for fast domain adaption. We propose to split parameters in the model into two groups: model parameters and meta parameters. The former are used to model the translation while the latter are used to adjust the representational space to generalize the model to different domains. We mimic the domain adaptation of the machine translation model to low-resource domains using multiple translation tasks on different domains. A new training strategy based on meta-learning is developed along with the proposed model to update the model parameters and meta parameters alternately. Experiments on datasets of different domains showed substantial improvements of NMT performances on a limited amount of data.

Timeline Generation, through generating news timelines from the massive data of news corpus, aims at providing readers with summaries about the evolvement of an event. It is a new challenge of summarization that combines salience ranking with novelty detection. For a long-term public event, the main topic usually includes many different sub-topics at varying epochs, which also has its own evolving patterns. Existing approaches fail to utilize such hierarchical topic structure involved in the news corpus for timeline generation. In this paper, we develop a novel time-dependent Hierarchical Dirichlet Tree Model (tHDT) for timeline generation. Our model can aptly detect different levels of topic information in corpus and the structure is further used for sentence selection. Based on the topic distribution mined from tHDT, sentences are selected through an overall consideration of relevance, coherence and coverage. We develop experimental systems to compare different rival algorithms on 8 long-term events of public concern. The performance comparison demonstrates the effectiveness of our proposed model in terms of ROUGE metrics.

Text-level discourse parsing remains a challenge: most approaches employ fea-tures that fail to capture the intentional, se-mantic, and syntactic aspects that govern discourse coherence. In this paper, we pro-pose a recursive model for discourse pars-ing that jointly models distributed repre-sentations for clauses, sentences, and en-tire discourses. The learned representa-tions can to some extent learn the seman-tic and intentional import of words and larger discourse units automatically,. The proposed framework obtains comparable performance regarding standard discours-ing parsing evaluations when compared against current state-of-art systems. 1