Search

Your search keyword '"Lee, Jinu"' showing total 225 results
Start Over Author "Lee, Jinu"
225 results on '"Lee, Jinu"'

1. SymBa: Symbolic Backward Chaining for Structured Natural Language Reasoning

Author

Lee, Jinu and Hwang, Wonseok

Subjects
Computer Science - Computation and Language
Abstract

To improve the performance and explainability of LLM-based natural language reasoning, structured reasoning can be applied to generate explicitly structured proofs. Among different methods for structured reasoning, we specifically focus on backward chaining, where the proof goal is recursively decomposed to subgoals by searching and applying rules. We argue that current LLM-based backward chaining systems (e.g. Least-to-most prompting and LAMBADA) are incomplete, as they omit crucial algorithmic components identified from the classic backward chaining algorithm (SLD Resolution) in computational logic. To this end, we propose a novel backward chaining system, SymBa (Symbolic Backward Chaining), which integrates a symbolic solver and an LLM. In SymBa, the solver controls the proof process, and the LLM is only called when the solver requires new information to complete the proof. Empowered by completeness, SymBa achieves a significant improvement in deductive, relational, and arithmetic reasoning benchmarks compared to the baselines., Comment: 18 pages (8 pages for main text),11 figures

Published
2024

8. Deep learning approach in multi-scale prediction of turbulent mixing-layer

Author

Lee, Jinu, Lee, Sangseung, and You, Donghyun

Subjects
Physics - Computational Physics, Physics - Fluid Dynamics
Abstract

Achievement of solutions in Navier-Stokes equation is one of challenging quests, especially for its closure problem. For achievement of particular solutions, there are variety of numerical simulations including Direct Numerical Simulation (DNS) or Large Eddy Simulation (LES). These methods analyze flow physics through efficient reduced-order modeling such as proper orthogonal decomposition or Koopman method, showing prominent fidelity in fluid dynamics. Generative adversarial network (GAN) is a reprint of neurons in brain as combinations of linear operations, using competition between generator and discriminator. Current paper propose deep learning network for prediction of small-scale movements with large-scale inspections only, using GAN. Therefore DNS result of three-dimensional mixing-layer was filtered blurring out the small-scaled structures, then is predicted of its detailed structures, utilizing Generative Adversarial Network (GAN). This enables multi-resolution analysis being asked to predict fine-resolution solution with only inspection of blurry one. Within the grid scale, current paper present deep learning approach of modeling small scale features in turbulent flow. The presented method is expected to have its novelty in utilization of unprocessed simulation data, achievement of 3D structures in prediction by processing 3D convolutions, and predicting precise solution with less computational costs., Comment: 21 pages

Published
2018

15. SymBa: Symbolic Backward Chaining for Multi-step Natural Language Reasoning

Author

Lee, Jinu, Hwang, Wonseok, Lee, Jinu, and Hwang, Wonseok

Abstract

Large Language Models (LLMs) have recently demonstrated remarkable reasoning ability as in Chain-of-thought prompting, but faithful multi-step reasoning remains a challenge. We specifically focus on backward chaining, where the query is recursively decomposed using logical rules until proven. To address the limitations of current backward chaining implementations, we propose SymBa (Symbolic Backward Chaining). In SymBa, the symbolic top-down solver controls the entire proof process and the LLM is called to generate a single reasoning step only when the solver encounters a dead end. By this novel solver-LLM integration, while being able to produce an interpretable, structured proof, SymBa achieves significant improvement in performance, proof faithfulness, and efficiency in diverse multi-step reasoning benchmarks (ProofWriter, Birds-Electricity, GSM8k, CLUTRR-TF, ECtHR Article 6) compared to backward chaining baselines., Comment: 22 pages (8 pages for main text),9 figures

Published
2024

26. Serum albumin maintains Wnt water-solubility and activity

Author

Yeo, Joo Hye, primary, Kwon, Soon Sung, additional, Chae, Jiyeon, additional, Kusen, Ines, additional, Han, Jaeeun, additional, Lim, Ju Yeon, additional, Cheong, Jae-Ho, additional, Kim, Taeil, additional, Jung, Yang Ouk, additional, Kim, Chul Hoon, additional, and Lee, Jinu, additional

Published
2023
Full Text
View/download PDF

42. Identification of Cx45 as a Major Component of GJs in HeLa Cells

Author

Choi, Eun Ju, Palacios-Prado, Nicolás, Sáez, Juan C., and Lee, Jinu

Subjects
gap junction, iodide-yellow fluorescent protein GJIC assay, lcsh:QR1-502, sense organs, HeLa cell, CRISPR/Cas9, lcsh:Microbiology
Abstract

&nbsp, Gap junctions (GJs) are intercellular channels that connect adjacent cells electrically and metabolically. The iodide-yellow fluorescent protein (I-YFP) gap junctional intercellular communication (GJIC) assay is a recently developed method with high sensitivity. HeLa cells have been widely used as GJ-deficient cells for GJ-related research. Herein, we present evidence showing that HeLa cells have functional GJs comprising connexin (Cx) 45 using the I-YFP GJ assay and CRISPR/Cas9 system. We conducted the I-YFP GJIC assay in HeLa cells, which revealed a weak level of GJIC that could not be detected by the Lucifer yellow scrape-loading assay. The mRNA expression of GJB5 (Cx31.1), GJA1 (Cx43), and GJC1 (Cx45) was detected in HeLa cells by RT-PCR analysis. Knocking out GJC1 (Cx45) abolished GJIC, as analyzed by the I-YFP assay and dual whole-cell patch-clamp assay. These results suggest that HeLa cells express Cx45-based GJs and that the I-YFP GJIC assay can be used for cells with weak GJIC, such as Cx45-expressing HeLa cells. Further, GJC1 (Cx45)-knockout HeLa cells are more suitable as a GJ-null cell model for transfection experiments than wild-type HeLa cells. This experimental design was successfully applied to knock out Cx43 expression and GJIC in A549 lung cancer cells and can thus be used to identify major Cxs in other cell types and to establish GJ assay systems for different Cxs.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results