Large language models (LLMs) demonstrate impressive performance on downstream tasks through in-context learning(ICL). However, there is a significant gap between their performance in Named Entity Recognition (NER) and in fine-tuning methods. We believe this discrepancy is due to inconsistencies in labeling definitions in NER. In addition, recent research indicates that LLMs do not learn the specific input-label mappings from the demonstrations. Therefore, we argue that using examples to implicitly capture the mapping between inputs and labels in in-context learning is not suitable for NER. Instead, it requires explicitly informing the model of the range of entities contained in the labels, such as annotation guidelines. In this paper, we propose GuideNER, which uses LLMs to summarize concise annotation guidelines as contextual information in ICL. We have conducted experiments on widely used NER datasets, and the experimental results indicate that our method can consistently and significantly outperform state-of-the-art methods, while using shorter prompts. Especially on the GENIA dataset, our model outperforms the previous state-of-the-art model by 12.63 F1 scores.

Empathetic response generation is a significant domain in Natural Language Processing (NLP). Its development is a critical step toward achieving humanized AI systems. However, current evaluations of empathetic dialogue models are primarily single-turn and static, leading to bias between evaluation results and real-world multi-turn interaction performance. To overcome the longstanding challenge, we propose a novel Interactive Empathy Evaluation Framework (IEEF). It eliminates the bias by facilitating a human-free multi-turn interaction evaluation. Specifically, for human-free interaction, we design a user simulator using reinforcement learning, leveraging a reward model based on LLM scoring. For evalution, we introduce a series of empathy-related metrics based on LLM. The experiments show that IEEF’s evaluation results are highly correlated with real-world multi-turn interaction performance, demonstrating its alignment with human preferences in empathy evaluation.

Multimodal information extraction (MIE) has gained increasing attention, as it helps to accomplish information extraction by adding images as auxiliary information. By acquiring entity-related knowledge, knowledge generation methods can effectively enhance the performance of information extraction models. However, current knowledge generation methods have two weaknesses: (1) they often generate knowledge that includes task-irrelevant information causing redundancy and negatively impacting model performance; (2) they typically concatenate knowledge and text input directly together, ignoring the stylistic and contextual differences arising from their different sources. To address these issues, we propose Low-Redundancy Knowledge Generation and Modality-Aware Interaction (LRKG-MAI). Our approach leverages a large language model to generate task-relevant knowledge with minimal redundancy, while treating knowledge as a distinct modality that interacts with text within its own representation space. Extensive experiments demonstrate the effectiveness of our approach. The source code can be found at https://github.com/JinFish/LRKG-MAI.

Recently, multimodal named entity recognition (MNER) has emerged as a vital research area within named entity recognition. However, current MNER datasets and methods are predominantly based on text and a single accompanying image, leaving a significant research gap in MNER scenarios involving multiple images. To address the critical research gap and enhance the scope of MNER for real-world applications, we propose a novel human-annotated MNER dataset with multiple images called MNER-MI. Additionally, we construct a dataset named MNER-MI-Plus, derived from MNER-MI, to ensure its generality and applicability. Based on these datasets, we establish a comprehensive set of strong and representative baselines and we further propose a simple temporal prompt model with multiple images to address the new challenges in multi-image scenarios. We have conducted extensive experiments to demonstrate that considering multiple images provides a significant improvement over a single image and can offer substantial benefits for MNER. Furthermore, our proposed method achieves state-of-the-art results on both MNER-MI and MNER-MI-Plus, demonstrating its effectiveness. The datasets and source code can be found at https://github.com/JinFish/MNER-MI.

Recently, multimodal sentiment analysis from social media posts has received increasing attention, as it can effectively improve single-modality-based sentiment analysis by leveraging the complementary information between text and images. Despite their success, current methods still suffer from two weaknesses: (1) the current methods for obtaining image representations do not obtain sentiment information, which leads to a significant gap between image representations and results; (2) the current methods ignore the sentiments expressed by the symbols (emoticons, emojis) in the text, but these symbols can effectively reflect the user's sentiments. To address these issues, we propose a sentimental prompt framework with visual text encoder (SPFVTE). Specifically, for the first problem, instead of using the image representation directly, we project the image representation as a prompt and utilize the prompt learning to capture sentimental information in images by learning a sentiment-specific prompt. For the second problem, considering that people get the meanings of emojis and emoticons from their graphics, we propose to render the text as an image and use a visual text encoder to capture the sentiments contained in emojis and emoticons. We have conducted experiments on three public multimodal sentiment datasets, and the experimental results show that our method can significantly and consistently outperform the state-of-the-art methods. The datasets and source code can be found at https://github.com/JinFish/SPFVTE.

Succinctly summarizing dialogue is a task of growing interest, but inherent challenges, such as insufficient training data and low information density impede our ability to train abstractive models.In this work, we propose a novel curriculum-based prompt learning method with self-training to address these problems.Specifically, prompts are learned using a curriculum learning strategy that gradually increases the degree of prompt perturbation, thereby improving the dialogue understanding and modeling capabilities of our model.Unlabeled dialogue is incorporated by means of self-training so as to reduce the dependency on labeled data.We further investigate topic-aware prompts to better plan for the generation of summaries.Experiments confirm that our model substantially outperforms strong baselines and achieves new state-of-the-art results on the AMI and ICSI datasets.Human evaluations also show the superiority of our model with regard to the summary generation quality.

Pre-trained language models (PLMs) have shown remarkable performance in natural language processing tasks, whereas these approaches often require a massive amount of data. Due to the lack of sufficient training instances, it is challenging for existing PLMs to achieve good results on dialogue summarization. In this paper, we propose DynamicPET, a pattern-exploiting training (PET) based method for abstractive dialogue summarization, which leverages the recent prompt learning paradigm to boost the performance of PLMs. In contrast to PET, our method does not rely on any task-specific unlabeled data, but obtains strong performance on two dialogue summarization datasets, especially in the few-shot scenarios.