Jongwon Lee

Jongwon Lee, Su Yeon Choi, Timothy Bretl

This paper quantifies the performance of visual SLAM that leverages multi-scale fiducial markers (i.e., artificial landmarks that can be detected at a wide range of distances) to show its potential for reliable takeoff and landing navigation in rotorcraft. Prior work has shown that square markers with a black-and-white pattern of grid cells can be used to improve the performance of visual SLAM with color cameras. We extend this prior work to allow nested marker layouts. We evaluate performance during semi-autonomous takeoff and landing operations in a variety of environmental conditions by a DJI Matrice 300 RTK rotorcraft with two FLIR Blackfly color cameras, using RTK GNSS to obtain ground truth pose estimates. Performance measures include absolute trajectory error and the fraction of the number of estimated poses to the total frame. We release all of our results -- our dataset and the code of the implementation of the visual SLAM with fiducial markers -- to the public as open-source.

Younghoon Jeong, Juhyun Oh, Jaimeen Ahn et al.

Recent directions for offensive language detection are hierarchical modeling, identifying the type and the target of offensive language, and interpretability with offensive span annotation and prediction. These improvements are focused on English and do not transfer well to other languages because of cultural and linguistic differences. In this paper, we present the Korean Offensive Language Dataset (KOLD) comprising 40,429 comments, which are annotated hierarchically with the type and the target of offensive language, accompanied by annotations of the corresponding text spans. We collect the comments from NAVER news and YouTube platform and provide the titles of the articles and videos as the context information for the annotation process. We use these annotated comments as training data for Korean BERT and RoBERTa models and find that they are effective at offensiveness detection, target classification, and target span detection while having room for improvement for target group classification and offensive span detection. We discover that the target group distribution differs drastically from the existing English datasets, and observe that providing the context information improves the model performance in offensiveness detection (+0.3), target classification (+1.5), and target group classification (+13.1). We publicly release the dataset and baseline models.

Jongwon Lee, Su Yeon Choi, David Hanley et al.

This paper presents a comparative study of three modes for mobile robot localization based on visual SLAM using fiducial markers (i.e., square-shaped artificial landmarks with a black-and-white grid pattern): SLAM, SLAM with a prior map, and localization with a prior map. The reason for comparing the SLAM-based approaches leveraging fiducial markers is because previous work has shown their superior performance over feature-only methods, with less computational burden compared to methods that use both feature and marker detection without compromising the localization performance. The evaluation is conducted using indoor image sequences captured with a hand-held camera containing multiple fiducial markers in the environment. The performance metrics include absolute trajectory error and runtime for the optimization process per frame. In particular, for the last two modes (SLAM and localization with a prior map), we evaluate their performances by perturbing the quality of prior map to study the extent to which each mode is tolerant to such perturbations. Hardware experiments show consistent trajectory error levels across the three modes, with the localization mode exhibiting the shortest runtime among them. Yet, with map perturbations, SLAM with a prior map maintains performance, while localization mode degrades in both aspects.

Jean Seo, Gibaeg Kim, Kihun Shin et al.

We introduce EPAG, a benchmark dataset and framework designed for Evaluating the Pre-consultation Ability of LLMs using diagnostic Guidelines. LLMs are evaluated directly through HPI-diagnostic guideline comparison and indirectly through disease diagnosis. In our experiments, we observe that small open-source models fine-tuned with a well-curated, task-specific dataset can outperform frontier LLMs in pre-consultation. Additionally, we find that increased amount of HPI (History of Present Illness) does not necessarily lead to improved diagnostic performance. Further experiments reveal that the language of pre-consultation influences the characteristics of the dialogue. By open-sourcing our dataset and evaluation pipeline on https://github.com/seemdog/EPAG, we aim to contribute to the evaluation and further development of LLM applications in real-world clinical settings.

Juhyun Oh, Nayeon Lee, Chani Jung et al.

Large Language Models (LLMs) often generate overly cautious and vague responses on sensitive topics, sacrificing helpfulness for safety. Existing evaluation frameworks lack systematic methods to identify and address specific weaknesses in responses to sensitive topics, making it difficult to improve both safety and helpfulness simultaneously. To address this, we introduce FINEST, a FINE-grained response evaluation taxonomy for Sensitive Topics, which breaks down helpfulness and harmlessness into errors across three main categories: Content, Logic, and Appropriateness. Experiments on a Korean-sensitive question dataset demonstrate that our score- and error-based improvement pipeline, guided by FINEST, significantly improves the model responses across all three categories, outperforming refinement without guidance. Notably, score-based improvement -- providing category-specific scores and justifications -- yields the most significant gains, reducing the error sentence ratio for Appropriateness by up to 33.09%. This work lays the foundation for a more explainable and comprehensive evaluation and improvement of LLM responses to sensitive questions.

Sungjoon Park, Jihyung Moon, Sungdong Kim et al.

We introduce Korean Language Understanding Evaluation (KLUE) benchmark. KLUE is a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification, SemanticTextual Similarity, Natural Language Inference, Named Entity Recognition, Relation Extraction, Dependency Parsing, Machine Reading Comprehension, and Dialogue State Tracking. We build all of the tasks from scratch from diverse source corpora while respecting copyrights, to ensure accessibility for anyone without any restrictions. With ethical considerations in mind, we carefully design annotation protocols. Along with the benchmark tasks and data, we provide suitable evaluation metrics and fine-tuning recipes for pretrained language models for each task. We furthermore release the pretrained language models (PLM), KLUE-BERT and KLUE-RoBERTa, to help reproducing baseline models on KLUE and thereby facilitate future research. We make a few interesting observations from the preliminary experiments using the proposed KLUE benchmark suite, already demonstrating the usefulness of this new benchmark suite. First, we find KLUE-RoBERTa-large outperforms other baselines, including multilingual PLMs and existing open-source Korean PLMs. Second, we see minimal degradation in performance even when we replace personally identifiable information from the pretraining corpus, suggesting that privacy and NLU capability are not at odds with each other. Lastly, we find that using BPE tokenization in combination with morpheme-level pre-tokenization is effective in tasks involving morpheme-level tagging, detection and generation. In addition to accelerating Korean NLP research, our comprehensive documentation on creating KLUE will facilitate creating similar resources for other languages in the future. KLUE is available at https://klue-benchmark.com.

Jongwon Lee, Timothy Bretl

In this paper, we present a method for localizing a query image with respect to a precomputed 3D Gaussian Splatting (3DGS) scene representation. First, the method uses 3DGS to render a synthetic RGBD image at some initial pose estimate. Second, it establishes 2D-2D correspondences between the query image and this synthetic image. Third, it uses the depth map to lift the 2D-2D correspondences to 2D-3D correspondences and solves a perspective-n-point (PnP) problem to produce a final pose estimate. Results from evaluation across three existing datasets with 38 scenes and over 2,700 test images show that our method significantly reduces both inference time (by over two orders of magnitude, from more than 10 seconds to as fast as 0.1 seconds) and estimation error compared to baseline methods that use photometric loss minimization. Results also show that our method tolerates large errors in the initial pose estimate of up to 55° in rotation and 1.1 units in translation (normalized by scene scale), achieving final pose errors of less than 5° in rotation and 0.05 units in translation on 90% of images from the Synthetic NeRF and Mip-NeRF360 datasets and on 42% of images from the more challenging Tanks and Temples dataset.

Doyoung Kim, Jongwon Lee, Jinho Park et al.

Language models' ability to extrapolate learned behaviors to novel, more complex environments beyond their training scope is highly unknown. This study introduces a path planning task in a textualized Gridworld to probe language models' extrapolation capabilities. We show that conventional approaches, including next token prediction and Chain of Thought (CoT) finetuning, fail to extrapolate in larger, unseen environments. Inspired by human cognition and dual process theory, we propose cognitive maps for path planning, a novel CoT framework that simulates humanlike mental representations. Our experiments show that cognitive maps not only enhance extrapolation to unseen environments but also exhibit humanlike characteristics through structured mental simulation and rapid adaptation. Our finding that these cognitive maps require specialized training schemes and cannot be induced through simple prompting opens up important questions about developing general-purpose cognitive maps in language models. Our comparison with exploration-based methods further illuminates the complementary strengths of offline planning and online exploration.

Haejun Lee, Akhil Kedia, Jongwon Lee et al.

Recent approaches to Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank passages with a separate reranker model and generate an answer using another reader model. Despite performing related tasks, the models have separate parameters and are weakly-coupled during training. We propose casting the retriever and the reranker as internal passage-wise attention mechanisms applied sequentially within the transformer architecture and feeding computed representations to the reader, with the hidden representations progressively refined at each stage. This allows us to use a single question answering model trained end-to-end, which is a more efficient use of model capacity and also leads to better gradient flow. We present a pre-training method to effectively train this architecture and evaluate our model on the Natural Questions and TriviaQA open datasets. For a fixed parameter budget, our model outperforms the previous state-of-the-art model by 1.0 and 0.7 exact match scores.