Soo-joon Choi

Ji-jun Park, Soo-joon Choi

Agricultural meteorological recommendations are crucial for enhancing crop productivity and sustainability by providing farmers with actionable insights based on weather forecasts, soil conditions, and crop-specific data. This paper presents a novel approach that leverages large language models (LLMs) and prompt engineering to improve the accuracy and relevance of these recommendations. We designed a multi-round prompt framework to iteratively refine recommendations using updated data and feedback, implemented on ChatGPT, Claude2, and GPT-4. Our method was evaluated against baseline models and a Chain-of-Thought (CoT) approach using manually collected datasets. The results demonstrate significant improvements in accuracy and contextual relevance, with our approach achieving up to 90\% accuracy and high GPT-4 scores. Additional validation through real-world pilot studies further confirmed the practical benefits of our method, highlighting its potential to transform agricultural practices and decision-making.

Ji-jun Park, Soo-joon Choi, Jiwon Jeong et al.

Large language models (LLMs) frequently encode factual and reasoning knowledge in their internal representations that is not faithfully reflected in their surface-level outputs -- a phenomenon known as \emph{latent knowledge}. Existing approaches to eliciting latent knowledge, such as Contrastive Consistency Search (CCS), rely on contrastive activation patterns and struggle with complex multi-step reasoning tasks, while mechanistic interpretability tools have primarily been used to \emph{understand} model behavior rather than to \emph{extract} hidden knowledge. We present \textbf{MechELK}, a unified three-stage framework that bridges mechanistic interpretability and latent knowledge elicitation. MechELK operates through: (1) \textbf{Locate} -- using Sparse Autoencoder (SAE) feature analysis and activation patching to identify knowledge-bearing representations; (2) \textbf{Verify} -- employing causal probing to distinguish genuine latent knowledge from spurious correlations; and (3) \textbf{Elicit} -- applying representation engineering to surface hidden knowledge without modifying model weights. Evaluated on TruthfulQA, a curated Deceptive Alignment benchmark, and the Quirky LM dataset, MechELK achieves an average elicitation accuracy of 84.7\%, outperforming CCS by 6.2\% and direct linear probing by 9.1\%. Crucially, MechELK successfully identifies latent knowledge in 78.3\% of cases where the model's surface output is incorrect or evasive, demonstrating its utility for AI safety applications including deceptive alignment detection.

Soo-joon Choi, Ji-jun Park

Financial event entity extraction is a crucial task for analyzing market dynamics and building financial knowledge graphs, yet it presents significant challenges due to the specialized language and complex structures in financial texts. Traditional approaches often rely on sequence labeling models, which can struggle with long-range dependencies and the inherent complexity of extracting multiple, potentially overlapping entities. Motivated by the advanced language understanding and generative capabilities of Large Language Models (LLMs), we propose a novel method that reframes financial event entity extraction as a text-to-structured-output generation task. Our approach involves fine-tuning a pre-trained LLM using Parameter-Efficient Fine-Tuning (PEFT) to directly generate a structured representation, such as a JSON object, containing the extracted entities and their precise character spans from the input text. We evaluate our method on the challenging CCKS 2019 Financial Event Entity Extraction dataset, comparing its performance against strong sequence labeling baselines, including SEBERTNets and sebertNets. Experimental results demonstrate that our generative LLM method achieves a new state-of-the-art F1 score on this benchmark, significantly outperforming previous methods. Through detailed quantitative analysis across event types, entity types, and instance complexity, as well as human evaluation, we show that our approach is more effective at handling the nuances of financial text and extracting high-quality entities. This work validates the potential of applying generative LLMs directly to complex, domain-specific information extraction tasks requiring structured output.

Ji-jun Park, Soo-joon Choi

Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress, they often struggle to capture the causal and temporal dynamics inherent in complex video sequences. To address this limitation, we propose an enhanced framework that integrates a Causal-Temporal Reasoning Module (CTRM) into state-of-the-art LVLMs. CTRM comprises two key components: the Causal Dynamics Encoder (CDE) and the Temporal Relational Learner (TRL), which collectively encode causal dependencies and temporal consistency from video frames. We further design a multi-stage learning strategy to optimize the model, combining pre-training on large-scale video-text datasets, fine-tuning on causally annotated data, and contrastive alignment for better embedding coherence. Experimental results on standard benchmarks such as MSVD and MSR-VTT demonstrate that our method outperforms existing approaches in both automatic metrics (CIDEr, BLEU-4, ROUGE-L) and human evaluations, achieving more fluent, coherent, and relevant captions. These results validate the effectiveness of our approach in generating captions with enriched causal-temporal narratives.