arXiv subjects

Seonho An

Publications and source records attributed to Seonho An.

5 recordsLinked to original sources

arXiv2026

GraphContainer: A Unified Platform for Comparing and Debugging Graph RAG Methods

Graph RAG mitigates hallucinations and stale knowledge in LLMs, particularly for multi-hop question answering. However, existing approaches remain highly fragmented and incompatible. The structural heterogeneity of graph formats across different frameworks and the lack of granular visualization tools make it exceedingly difficult to evaluate and compare retrieval behaviors. To bridge this gap, we propose GraphContainer, a novel platform designed to unify and visualize diverse graph RAG workflows. GraphContainer features two key components: (1) a Unified Graph Representation (UGR) layer that seamlessly standardizes multi-format graphs, and (2) a Graph Recorder that tracks and visually renders the step-by-step retrieval process. Through an interactive web interface, we demonstrate GraphContainer's ability to import heterogeneous graphs and perform live, traceable visual debugging of graph RAG methods. Ultimately, we show how GraphContainer enables controlled comparisons of various graph formats and retrieval strategies, lowering the barrier for researchers and practitioners to design optimal graph RAG pipelines. A demonstration video is available at https://youtu.be/O02eNJLwkU0.

cs.AI↗

arXiv2026

GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs

Graph RAG on corpus graphs enhances retrieval by leveraging intermediate node content as contextual clues to uncover unretrieved oracle nodes. However, existing methods suffer from two critical blind spots, namely semantically blind graph expansion and topology blind pruning, or else rely on prohibitively slow retrieval and generation interleaving. To address this, we formalize these limitations through an operational taxonomy and propose a retriever design that couples semantics-aware adding with graph-aware pruning under efficiency constraints. We instantiate this design as GraFine, which alternates between two refinement stages: Semantic Proximity eXpansion (SPX) for semantics-aware node addition, and a Graph Smoothing Reranker (GSR) for graph-aware pruning. Experiments on reference networks and text-rich knowledge graphs show that GraFine improves retrieval accuracy and generation quality while maintaining time-efficiency. Furthermore, we introduce Topological Recall (TR), a metric that quantifies the topological proximity between retrieved and oracle nodes. Our analysis using TR confirms that GraFine more effectively steers refinement toward undiscovered oracle nodes by leveraging intermediate contextual clues. Our code is available at this link: https://github.com/asmath472/GraFine.

cs.IR↗

arXiv2025

Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies

Masked diffusion models (MDMs) have recently emerged as a novel framework for language modeling. MDMs generate sentences by iteratively denoising masked sequences, filling in [MASK] tokens step by step. Although MDMs support any-order sampling, performance is highly sensitive to the choice of which position to unmask next. Prior work typically relies on rule-based schedules (e.g., max-confidence, max-margin), which provide ad hoc improvements. In contrast, we replace these heuristics with a learned scheduler. Specifically, we cast denoising as a KL-regularized Markov decision process (MDP) with an explicit reference policy and optimize a regularized objective that admits policy improvement and convergence guarantees under standard assumptions. We prove that the optimized policy under this framework generates samples that more closely match the data distribution than heuristic schedules. Empirically, across four benchmarks, our learned policy consistently outperforms max-confidence: for example, on SUDOKU, where unmasking order is critical, it yields a 20.1% gain over random and a 11.2% gain over max-confidence. Code is available at https://github.com/chunsanHong/UPO.

cs.LG↗

arXiv2024

A Method for Detecting Legal Article Competition for Korean Criminal Law Using a Case-augmented Mention Graph

As social systems become increasingly complex, legal articles are also growing more intricate, making it progressively harder for humans to identify any potential competitions among them, particularly when drafting new laws or applying existing laws. Despite this challenge, no method for detecting such competitions has been proposed so far. In this paper, we propose a new legal AI task called Legal Article Competition Detection (LACD), which aims to identify competing articles within a given law. Our novel retrieval method, CAM-Re2, outperforms existing relevant methods, reducing false positives by 20.8% and false negatives by 8.3%, while achieving a 98.2% improvement in precision@5, for the LACD task. We release our codes at https://github.com/asmath472/LACD-public.

cs.CL↗

arXiv2024

PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers

In this paper, we conduct a study to utilize LLMs as a solution for decision making that requires complex data analysis. We define Decision QA as the task of answering the best decision, $d_{best}$, for a decision-making question $Q$, business rules $R$ and a database $D$. Since there is no benchmark that can examine Decision QA, we propose Decision QA benchmark, DQA. It has two scenarios, Locating and Building, constructed from two video games (Europa Universalis IV and Victoria 3) that have almost the same goal as Decision QA. To address Decision QA effectively, we also propose a new RAG technique called the iterative plan-then-retrieval augmented generation (PlanRAG). Our PlanRAG-based LM generates the plan for decision making as the first step, and the retriever generates the queries for data analysis as the second step. The proposed method outperforms the state-of-the-art iterative RAG method by 15.8% in the Locating scenario and by 7.4% in the Building scenario, respectively. We release our code and benchmark at https://github.com/myeon9h/PlanRAG.

cs.CL↗