Using LLMs to Bridge the Gaps in QA Test Plans at Firefox
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
As software systems grow in scale and complexity, ensuring their reliability becomes increasingly challenging due to factors like diverse platforms, rapid release cycles, and evolving user needs. This places greater demands on software quality assurance (QA), where comprehensive test planning is crucial. However, in addition to this process being manual and time-consuming, skilled QA engineers may potentially overlook critical scenarios. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">To bridge this gap, we used an LLM, GPT-4 Turbo, to generate test plans for eight Firefox features, evaluating them for novelty, validity, and relevance. Our results showed that 27% of the test cases in LLM-generated plans surfaced previously missed test scenarios the QA team deemed valuable, while 50.5% replicated existing ones. Although 22.5% were invalid and out of scope, our approach shows potential for improving test coverage. In this paper, we share our experience with this methodology and offer insights for SE/QA practitioners integrating LLMs into their workflows.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it