activity
20242026
most citedClotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs

2 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing cs.SEShow all

10 papers · 1 filter

cs.SE20262 cited

Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs

Juyeon Yoon, Somin Kim, Robert Feldt +1

Software increasingly relies on the emergent capabilities of Large Language Models (LLMs), from natural language understanding to program analysis and generation. Yet testing them…

cs.SE2026

Understanding on the Edge: LLM-generated Boundary Test Explanations

Sabinakhon Akbarova, Felix Dobslaw, Robert Feldt

Boundary value analysis and testing (BVT) is fundamental in software quality assurance because faults tend to cluster at input extremes, yet testers often struggle to understand an…

cs.SE2025

From Challenge to Change: Design Principles for AI Transformations

Theocharis Tavantzis, Stefano Lambiase, Daniel Russo +1

The rapid rise of Artificial Intelligence (AI) is reshaping Software Engineering (SE), creating new opportunities while introducing human-centered challenges. Although prior work n…

cs.SE2025

Large Language Models in Thematic Analysis: Prompt Engineering, Evaluation, and Guidelines for Qualitative Software Engineering Research

Cristina Martinez Montes, Robert Feldt, Cristina Miguel Martos +3

As artificial intelligence advances, large language models (LLMs) are entering qualitative research workflows, yet no reproducible methods exist for integrating them into establish…

cs.SE2025

Challenges in Testing Large Language Model Based Software: A Faceted Taxonomy

Felix Dobslaw, Robert Feldt, Juyeon Yoon +1

Large Language Models (LLMs) and Multi-Agent LLMs (MALLMs) introduce non-determinism unlike traditional or machine learning software, requiring new approaches to verifying correctn…

cs.SE2025

SETBVE: Quality-Diversity Driven Exploration of Software Boundary Behaviors

Sabinakhon Akbarova, Felix Dobslaw, Francisco Gomes de Oliveira Neto +1

Software systems exhibit distinct behaviors based on input characteristics, and failures often occur at the boundaries between input domains. Traditional Boundary Value Analysis (B…