works on

From the 2 of 16 linked papers with an AI index.

activity
20242026
collaborators

16 papers

cs.SE2026

How Well Do LLMs Generate Taxonomies in the SE Domain? A Multi-perspective Evaluation Framework

Sota Nakashima, Yuta Ishimoto, Masanari Kondo +2

Taxonomies provide a shared conceptual framework for organizing heterogeneous observations in software engineering (SE) research. Manually constructing such taxonomies is labor-int…

cs.SE2026

Directed Symbolic Execution for Vulnerability Discovery: An LLM-Guided Approach in KLEE

Lingfeng Chen, Tao Xiao, Masanari Kondo +1

Symbolic execution effectively discovers security violations but suffers from path explosion. Engines like KLEE therefore use path prioritization heuristics to order state explorat…

cs.SE2026

RepTran: Search-Based Repair of Transformer Models

Yuta Ishimoto, Paolo Arcaini, Fuyuki Ishikawa +3

The paper introduces RepTran, a search‑based method that repairs Transformer models by identifying and optimizing suspicious feed‑forward network weights using variance‑based and b…

cs.SE2026

ThinkLog: Leveraging Reasoning for Log Statement Generation

Kazuki Kusama, Honglin Shu, Masanari Kondo +2

ThinkLog uses large language models with reasoning prompts to automatically decide where to insert logs, what severity to assign, and how to phrase log messages, improving the accu…

cs.SE2026

Exploring the Potential of Program Flowcharts on Code Generation Using Multimodal LLMs

Yuki Toi, Tao Xiao, Kazushi Tomoto +2

In recent years, Large Language Models (LLMs) have made significant strides, leading to the emergence of multimodal LLMs capable of processing diverse inputs such as images and aud…

cs.SE2026

Leveraging Language Models for Log Statement Generation in Multilingual Scenarios: How Far Are We?

Kazuki Kusama, Honglin Shu, Masanari Kondo +1

Log statements capture critical information for software maintenance activities such as testing, debugging, and failure analysis. Because of this importance, developers must carefu…