Min-Jun Kim

Minjun Kim, Seungwoo Song, Youhan Lee et al.

The current research direction in generative models, such as the recently developed GPT4, aims to find relevant knowledge information for multimodal and multilingual inputs to provide answers. Under these research circumstances, the demand for multilingual evaluation of visual question answering (VQA) tasks, a representative task of multimodal systems, has increased. Accordingly, we propose a bilingual outside-knowledge VQA (BOK-VQA) dataset in this study that can be extended to multilingualism. The proposed data include 17K images, 17K question-answer pairs for both Korean and English and 280K instances of knowledge information related to question-answer content. We also present a framework that can effectively inject knowledge information into a VQA system by pretraining the knowledge information of BOK-VQA data in the form of graph embeddings. Finally, through in-depth analysis, we demonstrated the actual effect of the knowledge information contained in the constructed training data on VQA.

Dongjae Shin, Hyeonseok Lim, Inho Won et al.

The impressive development of large language models (LLMs) is expanding into the realm of large multimodal models (LMMs), which incorporate multiple types of data beyond text. However, the nature of multimodal models leads to significant expenses in the creation of training data. Furthermore, constructing multilingual data for LMMs presents its own set of challenges due to language diversity and complexity. Therefore, in this study, we propose two cost-effective methods to solve this problem: (1) vocabulary expansion and pretraining of multilingual LLM for specific languages, and (2) automatic and elaborate construction of multimodal datasets using GPT4-V. Based on015 these methods, we constructed a 91K English-Korean-Chinese multilingual, multimodal training dataset. Additionally, we developed a bilingual multimodal model that exhibits excellent performance in both Korean and English, surpassing existing approaches.

Haewon Park, Gyubin Choi, Minjun Kim et al.

Knowledge editing (KE) methods offer an efficient way to modify knowledge in large language models. Current KE evaluations typically assess editing success by considering only the edited knowledge without any preceding contexts. In real-world applications, however, preceding contexts often trigger the retrieval of the original knowledge and undermine the intended edit. To address this issue, we develop CHED -- a benchmark designed to evaluate the context robustness of KE methods. Evaluations on CHED show that they often fail when preceding contexts are present. To mitigate this shortcoming, we introduce CoRE, a KE method designed to strengthen context robustness by minimizing context-sensitive variance in hidden states of the model for edited knowledge. This method not only improves the editing success rate in situations where a preceding context is present but also preserves the overall capabilities of the model. We provide an in-depth analysis of the differing impacts of preceding contexts when introduced as user utterances versus assistant responses, and we dissect attention-score patterns to assess how specific tokens influence editing success.

Seungcheol Park, Jeongin Bae, Beomseok Kwon et al.

How can we quantize large language models while preserving accuracy? Quantization is essential for deploying large language models (LLMs) efficiently. Binary-coding quantization (BCQ) and uniform quantization (UQ) are promising quantization schemes that have strong expressiveness and optimizability, respectively. However, neither scheme leverages both advantages. In this paper, we propose UniQuanF (Unified Quantization with Flexible Mapping), an accurate quantization method for LLMs. UniQuanF harnesses both strong expressiveness and optimizability by unifying the flexible mapping technique in UQ and non-uniform quantization levels of BCQ. We propose unified initialization, and local and periodic mapping techniques to optimize the parameters in UniQuanF precisely. After optimization, our unification theorem removes computational and memory overhead, allowing us to utilize the superior accuracy of UniQuanF without extra deployment costs induced by the unification. Experimental results demonstrate that UniQuanF outperforms existing UQ and BCQ methods, achieving up to 4.60% higher accuracy on GSM8K benchmark.

Jinwoo Ahn, Junhyeok Park, Min-Jun Kim et al.

In this paper, the solution of HYU MLLAB KT Team to the Multimodal Algorithmic Reasoning Task: SMART-101 CVPR 2024 Challenge is presented. Beyond conventional visual question-answering problems, the SMART-101 challenge aims to achieve human-level multimodal understanding by tackling complex visio-linguistic puzzles designed for children in the 6-8 age group. To solve this problem, we suggest two main ideas. First, to utilize the reasoning ability of a large-scale language model (LLM), the given visual cues (images) are grounded in the text modality. For this purpose, we generate highly detailed text captions that describe the context of the image and use these captions as input for the LLM. Second, due to the nature of puzzle images, which often contain various geometric visual patterns, we utilize an object detection algorithm to ensure these patterns are not overlooked in the captioning process. We employed the SAM algorithm, which can detect various-size objects, to capture the visual features of these geometric patterns and used this information as input for the LLM. Under the puzzle split configuration, we achieved an option selection accuracy Oacc of 29.5 on the test set and a weighted option selection accuracy (WOSA) of 27.1 on the challenge set.

Yiding Cao, Yingjun Dong, Minjun Kim et al.

Collective design and innovation are crucial in organizations. To investigate how the collective design and innovation processes would be affected by the diversity of knowledge and background of collective individual members, we conducted three collaborative design task experiments which involved nearly 300 participants who worked together anonymously in a social network structure using a custom-made computer-mediated collaboration platform. We compared the idea generation activity among three different background distribution conditions (clustered, random, and dispersed) with the help of the "doc2vec" text representation machine learning algorithm. We also developed a new method called "Idea Geography" to visualize the idea utility terrain on a 2D problem domain. The results showed that groups with random background allocation tended to produce the best design idea with highest utility values. It was also suggested that the diversity of participants' backgrounds distribution on the network might interact with each other to affect the diversity of ideas generated. The proposed idea geography successfully visualized that the collective design processes did find the high utility area through exploration and exploitation in collaborative work.

Minjun Kim, Hiroki Sayama

Text classification is one of the most critical areas in machine learning and artificial intelligence research. It has been actively adopted in many business applications such as conversational intelligence systems, news articles categorizations, sentiment analysis, emotion detection systems, and many other recommendation systems in our daily life. One of the problems in supervised text classification models is that the models' performance depends heavily on the quality of data labeling that is typically done by humans. In this study, we propose a new network community detection-based approach to automatically label and classify text data into multiclass value spaces. Specifically, we build networks with sentences as the network nodes and pairwise cosine similarities between the Term Frequency-Inversed Document Frequency (TFIDF) vector representations of the sentences as the network link weights. We use the Louvain method to detect the communities in the sentence networks. We train and test the Support Vector Machine and the Random Forest models on both the human-labeled data and network community detection labeled data. Results showed that models with the data labeled by the network community detection outperformed the models with the human-labeled data by 2.68-3.75% of classification accuracy. Our method may help developments of more accurate conversational intelligence and other text classification systems.