Ensuring consistent persona in interactive AI systems presents a significant challenge, especially in diverse application scenarios ranging from virtual assistants to customer service bots. Such capability is often constrained by the system's understanding of direct and explicit persona conflicts. Traditional approaches primarily focus on detecting discrepancies between machine responses and its predefined profile, or the contextual inconsistencies between the responses at the semantic level rather than the persona level. Due to the lack of a comprehensive persona-specific Commonsense Knowledge Graph, some indirect and implicit persona inconsistencies between machine responses can hardly be identified. In this paper, we build the first persona commonsense knowledge graph (PersonaKG), based on which we then construct a large-scale persona consistency dialogue dataset (PersonaCOM) containing both explicit and implicit persona conflicts between machine responses. With the guidance of the persona commonsense knowledge, we propose a Recognize-Rewrite framework (R2) which first recognizes the responses that are inconsistent in persona with the previous responses, and then rewrites them into consistent ones. The empirical study demonstrates that utilizing R2 method on PersonaCOM with PersonaKG results in a significant improvement of 12.20% in automatic metrics and 10.09% in manual evaluation compared to not using the R2 method and PersonaKG.

Large Language Models (LLMs) exhibit remarkable capabilities across various downstream tasks, including empathetic dialogues. However, a non-trivial question arises: Do they possess high-context empathy and can they generate emotional interactions with humans? High-context empathy, which tends to be more indirect and concise like Chinese-style empathy, differs from the current empathy capabilities of LLMs. These capabilities are predominantly low-context empathy, which is often direct and lengthy, resembling English-style empathy. In this paper, We first construct a comprehensive Chinese High-context Empathy Dialogue dataset (HED), which consists of emotional, role-based emotional, personality-based emotional, and role-personality-based emotional dialogues. Next, we explore whether LLMs have high-context empathy in conversations. After that, we propose an innovative High-context Empathy Network (HEN) to improve LLMs' capabilities in generating high-context empathetic responses. Our empirical study demonstrates that there is much room for LLMs in generating high-context empathetic responses, and the proposed HEN can not only significantly improve LLMs' capabilities in generating high-context empathetic responses, but also has positive effects for LLMs in solving similar sentiment-related tasks.

In medical research, clinical trials are pivotal. While prospective clinical research provides a systematic approach to collecting patient data, it grapples with challenges like long durations, increased costs, and most crucially, data scarcity. To address above-mentioned challenge, this paper introduces a novel approach: using cross-table generation to create relevant data. Unlike existing work focused on single-table operations, our method leverages data from multiple sources across various tables, integrating diverse data types and ensuring data consistency across multiple tables. We develop a new framework, MedTransTab, tailored for cross-table tabular data generation in the medical context. This framework extends our previous efforts and is built upon the newly constructed PMC-Struct, derived from an unstructured PMC-patient dataset. Our MedTransTab can generate high-quality patient records, synthesizing detailed biomedical information to align with real or simulated tables from multiple sources. The experiments show that the proposed method significantly improves performance in cross-table tasks. On the PMC-Struct-Plus dataset, we observe an average improvement of 28.85% in data generation and prediction. Similarly, on the Out-Of-Domain (OOD) dataset, there's an average improvement of 22.56%, indicating substantial progress in medical data analysis.

Medical dialogue models predominantly emphasize generating coherent and clinically accurate responses. However, in many clinical scenarios, time plays a pivotal role, often dictating subsequent patient management and interventions. Recognizing the latent importance of temporal dynamics, this paper introduces a novel dimension to medical dialogues: timestamps. We advocate that the integration of time-sensitive directives can profoundly impact medical advice, using an illustrative example of post-surgery care with and without timestamps. Our contributions are three-fold: Firstly, we highlight the intrinsic significance of timestamps in medical conversations, marking a paradigm shift in dialogue modeling. Secondly, we present an innovative dataset and framework explicitly tailored for time-stamped medical dialogues, facilitating the model to not only provide medical counsel but also chronologically outline care regimens. Lastly, empirical evaluations indicate our method's proficiency in time-stamped tasks and reveal an uptick in performance in broader medical Q&A domains. Through our endeavors, we aspire to set new benchmarks in patient-centric and time-sensitive medical dialogue systems.

Question understanding is an important issue to the success of a Knowledge-based Question Answering (KBQA) system.However, the existing study does not pay enough attention to this issue given that the questions in the existing KBQA datasets are usually expressed in simple and straightforward way. This is not in line with the actual linguistic conventions, which often use a lot of modifiers. To facilitate the study on evaluating and enhancing the question understanding ability of the KBQA systems, this paper proposes to construct a complex-modified question-answering (XMQAs) dataset based on existing KBQA datasets. With the help of knowledge bases and dictionaries, three kinds of modifiers are defined and applied to original simple-expressed questions. These modifiers could make the expression of these questions complex without changing their semantics. Based on XMQAs, we then propose a novel question understanding algorithm upon existing KBQA models, which greatly improves the robustness of their question understanding abilities. We conduct extensive experiments on XMQAs and two widely acknowledged KBQA datasets. The empirical results demonstrate that our proposed algorithm can improve the performance of KBQA models on not only the complex-modified questions, but also simple-expressed questions.

Recent years, Pre-trained Language models (PLMs) have swept into various fields of artificial intelligence and achieved great success. However, most PLMs, such as T5 and GPT3, have a huge amount of parameters, fine-tuning them is often expensive and time consuming, and storing them takes up a lot of space. Therefore, it is necessary to adopt a parameter-efficient approach to reduce parameters of PLMs in fine-tuning without compromising their performance in downstream tasks. In this paper, we design a novel adapter which only acts on self-attention outputs in PLMs. This adapter adopts element-wise linear transformation using Hadamard product, hence named as Hadamard adapter, requires the fewest parameters compared to previous parameter-efficient adapters. In addition, we also summarize some tuning patterns for Hadamard adapter shared by various downstream tasks, expecting to provide some guidance for further parameter reduction with shared adapters in future studies. The experiments conducted on the widely-used GLUE benchmark with several SOTA PLMs prove that the Hadamard adapter achieves competitive performance with only 0.033% parameters compared with full fine-tuning, and it has the fewest parameters compared with other adapters. Moreover, we further find that there is also some redundant layers in the Hadamard adapter which can be removed to achieve more parameter efficiency with only 0.022% parameters.

Large language models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems. However, a major drawback of LLMs is the issue of hallucination, where they generate unfaithful or inconsistent content that deviates from the input source, leading to severe consequences. In this paper, we propose a robust discriminator named RelD to effectively detect hallucination in LLMs' generated answers. RelD is trained on the constructed RelQA, a bilingual question-answering dialogue dataset along with answers generated by LLMs and a comprehensive set of metrics. Our experimental results demonstrate that the proposed RelD successfully detects hallucination in the answers generated by diverse LLMs. Moreover, it performs well in distinguishing hallucination in LLMs' generated answers from both in-distribution and out-of-distribution datasets. Additionally, we also conduct a thorough analysis of the types of hallucinations that occur and present valuable insights. This research significantly contributes to the detection of reliable answers generated by LLMs and holds noteworthy implications for mitigating hallucination in the future work.

Humor understanding is an important and challenging research in natural language processing. As the popularity of pre-trained language models (PLMs), some recent work makes preliminary attempts to adopt PLMs for humor recognition and generation. However, these simple attempts do not substantially answer the question: whether PLMs are capable of humor understanding? This paper is the first work that systematically investigates the humor understanding ability of PLMs. For this purpose, a comprehensive framework with three evaluation steps and four evaluation tasks is designed. We also construct a comprehensive Chinese humor dataset, which can fully meet all the data requirements of the proposed evaluation framework. Our empirical study on the Chinese humor dataset yields some valuable observations, which are of great guiding value for future optimization of PLMs in humor understanding and generation.

Interpreting the predictions of existing Question Answering (QA) models is critical to many real-world intelligent applications, such as QA systems for healthcare, education, and finance. However, existing QA models lack interpretability and provide no feedback or explanation for end-users to help them understand why a specific prediction is the answer to a question. In this research, we argue that the evidences of an answer is critical to enhancing the interpretability of QA models. Unlike previous research that simply extracts several sentence(s) in the context as evidence, we are the first to explicitly define the concept of evidence as the supporting facts in a context which are informative, concise, and readable. Besides, we provide effective strategies to quantitatively measure the informativeness, conciseness and readability of evidence. Furthermore, we propose Grow-and-Clip Evidence Distillation (GCED) algorithm to extract evidences from the contexts by trade-off informativeness, conciseness, and readability. We conduct extensive experiments on the SQuAD and TriviaQA datasets with several baseline models to evaluate the effect of GCED on interpreting answers to questions. Human evaluation are also carried out to check the quality of distilled evidences. Experimental results show that automatic distilled evidences have human-like informativeness, conciseness and readability, which can enhance the interpretability of the answers to questions.