Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs.However, this process may increase the model's dependence on user input, potentially leading to the unfiltered acceptance of misinformation and the generation of hallucinations.Existing studies primarily highlight that LLMs are receptive to external information that contradict their parametric knowledge, but little research has been conducted on the direct impact of instructiontuning on this phenomenon.In our study, we investigate the impact of instruction-tuning on LLM's susceptibility to misinformation.Our analysis reveals that instruction-tuned LLMs are significantly more likely to accept misinformation when it is presented by the user.A comparison with base models shows that instruction-tuning increases reliance on userprovided information, shifting susceptibility from the assistant role to the user role.Furthermore, we explore additional factors influencing misinformation susceptibility, such as the role of the user in prompt structure, misinformation length, and the presence of warnings in the system prompt.Our findings underscore the need for systematic approaches to mitigate unintended consequences of instruction-tuning and enhance the reliability of LLMs in realworld applications.

In this work, we introduce the Keep Emotional and Essential Memory (KEEM) dataset, a novel generation-based dataset designed to enhance memory updates in long-term conversational systems. Unlike existing approaches that rely on simple accumulation or operation-based methods, which often result in information conflicts and difficulties in accurately tracking a user’s current state, KEEM dynamically generates integrative memories. This process not only preserves essential factual information but also incorporates emotional context and causal relationships, enabling a more nuanced understanding of user interactions. By seamlessly updating a system’s memory with both emotional and essential data, our approach promotes deeper empathy and enhances the system’s ability to respond meaningfully in open-domain conversations.

This study addresses critical gaps in Automatic Essay Scoring (AES) systems and Large Language Models (LLMs) with regard to their ability to effectively identify and score harmful essays. Despite advancements in AES technology, current models often overlook ethically and morally problematic elements within essays, erroneously assigning high scores to essays that may propagate harmful opinions. In this study, we introduce the Harmful Essay Detection (HED) benchmark, which includes essays integrating sensitive topics such as racism and gender bias, to test the efficacy of various LLMs in recognizing and scoring harmful content. Our findings reveal that: (1) LLMs require further enhancement to accurately distinguish between harmful and argumentative essays, and (2) both current AES models and LLMs fail to consider the ethical dimensions of content during scoring. The study underscores the need for developing more robust AES systems that are sensitive to the ethical implications of the content they are scoring.

Existing studies on extractive summarization have primarily focused on scoring and selecting summary sentences independently. However, these models are limited to sentence-level extraction and tend to select highly generalized sentences while overlooking the overall content of a document. To effectively consider the semantics of a document, in this study, we introduce a novel machine reading comprehension (MRC) framework for extractive summarization (MRCSum) by setting a query as the title. Our framework enables MRCSum to consider the semantic coherence and relevance of summary sentences in relation to the overall content. In particular, when a title is not available, we generate a title-like query, which is expected to achieve the same effect as a title. Our title-like query consists of the topic and keywords to serve as information on the main topic or theme of the document. We conduct experiments in both Korean and English languages, evaluating the performance of MRCSum on datasets comprising both long and short summaries. Our results demonstrate the effectiveness of MRCSum in extractive summarization, showcasing its ability to generate concise and informative summaries with or without explicit titles. Furthermore, our MRCSum outperforms existing models by capturing the essence of the document content and producing more coherent summaries.

Nested Named Entity Recognition (NER) poses a significant challenge in Natural Language Processing (NLP), demanding sophisticated techniques to identify entities within entities.This research investigates the application of Large Language Models (LLMs) to nested NER, exploring methodologies from prior work and introducing specific reasoning techniques and instructions to improve LLM efficacy.Through experiments conducted on the ACE 2004, ACE 2005, and GENIA datasets, we evaluate the impact of these approaches on nested NER performance.Results indicate that output format critically influences nested NER performance, methodologies from previous works are less effective, and our nested NER-tailored instructions significantly enhance performance.Additionally, we find that label information and descriptions of nested cases are crucial in eliciting the capabilities of LLMs for nested NER, especially in specific domains (i.e., the GENIA dataset).However, these methods still do not outperform BERT-based models, highlighting the ongoing need for innovative approaches in nested NER with LLMs.

Emotional intelligence (EI) in artificial intelligence (AI), which refers to the ability of an AI to understand and respond appropriately to human emotions, has emerged as a crucial research topic.Recent studies have shown that large language models (LLMs) and vision large language models (VLLMs) possess EI and the ability to understand emotional stimuli in the form of text and images, respectively.However, factors influencing the emotion prediction performance of VLLMs in real-world conversational contexts have not been sufficiently explored.This study aims to analyze the key elements affecting the emotion prediction performance of VLLMs in conversational contexts systematically.To achieve this, we reconstructed the MELD dataset, which is based on the popular TV series Friends, and conducted experiments through three sub-tasks: overall emotion tone prediction, character emotion prediction, and contextually appropriate emotion expression selection.We evaluated the performance differences based on various model architectures (e.g., image encoders, modality alignment, and LLMs) and image scopes (e.g., entire scene, person, and facial expression).In addition, we investigated the impact of providing persona information on the emotion prediction performance of the models and analyzed how personality traits and speaking styles influenced the emotion prediction process.We conducted an in-depth analysis of the impact of various other factors, such as gender and regional biases, on the emotion prediction performance of VLLMs.The results revealed that these factors significantly influenced the model performance.

Most research on multimodal open-domain dialogue agents has focused on pretraining and multi-task learning using additional rich datasets beyond a given target dataset.However, methods for exploiting these additional datasets can be quite limited in real-world settings, creating a need for more efficient methods for constructing agents based solely on the target dataset.To address these issues, we present a new learning strategy called visionlanguage warm-up tasks for multimodal dialogue models (VLAW-MDM).This strategy does not require the use of large pretraining or multi-task datasets but rather relies solely on learning from target data.Moreover, our proposed approach automatically generates captions for images and incorporates them into the model's input to improve the contextualization of visual information.Using this novel approach, we empirically demonstrate that our learning strategy is effective for limited data and relatively small models.The result show that our method achieved comparable and in some cases superior performance compared to existing state-of-the-art models on various evaluation metrics.The code is available at https: //github.com/BeneciaLee/VLAW-MDM

Automated essay scoring (AES) is a crucial research area with potential applications in education and beyond. However, recent studies have primarily focused on AES models that evaluate essays within a specific domain or using a holistic score, leaving a gap in research and resources for more generalized models capable of assessing essays with detailed items from multiple perspectives. As evaluating and scoring essays based on complex traits is costly and time-consuming, datasets for such AES evaluations are limited. To address these issues, we developed a cross-prompt trait scoring AES model and proposed a suitable curriculum learning (CL) design. By devising difficulty scores and introducing the key curriculum method, we demonstrated its effectiveness compared to existing CL strategies in natural language understanding tasks.

Recently, various approaches have been developed for traffic analysis systems, ranging from Vehicle Detection Systems (VDS) to Mobile Detection Systems (MDS). However, VDS has limitations. For example, in actual driving situations such as intersections or exits, each lane may have different traffic conditions, revealing the limitations of traffic information provided by conventional VDS. In this paper, we propose a methodology to efficiently monitor the traffic condition and safety on the road by utilizing a LiDAR sensor installed on a vehicle to collect continuous traffic information about surrounding vehicles. To implement the Mobile Detection System (MDS), we collect point cloud data from LiDAR and detect the position and size of vehicles using a deep learning-based voxel-RCNN. We then convert the data into traffic information for analysis. Furthermore, we propose an efficient method for analyzing road hazards by introducing the MTTC method based on the TTC for hazard assessment. To evaluate the performance of the proposed method, we compare its reliability with that of conventional VDS and perform road hazards analysis using LiDAR-based probe vehicles with data collected directly from highways in Korea.