BM4LLM-SLR is a system designed to support researchers in the study selection phase of Systematic Literature Reviews (SLRs), making the use of Large Language Models (LLMs) more reliable and transparent.
Systematic Literature Reviews are essential for building scientific evidence, but they are labor-intensive. LLMs have the potential to assist, but they may introduce bias or inconsistencies if used alone. BM4LLM-SLR introduces an additional layer of bias mitigation, increasing trustworthiness through configurable confidence thresholds, reviewer involvement, and strictness controls.
To increase our trust in LLM decisions, we need to apply bias mitigation actions. For this, BM4LLM-SLR could be used which the overall process is described below:
Authors | Title | Year | Link |
---|---|---|---|
Kitchenham, B.; Charters, S. | Guidelines for Performing Systematic Literature Reviews in Software Engineering (EBSE-2007-01) | 2007 | Access |
Brereton, P.; Kitchenham, B.; Budgen, D.; Turner, M.; Khalil, M. | Lessons from Applying the Systematic Literature Review Process within the Software Engineering Domain | 2007 | Access |
Wohlin, C. | Guidelines for Snowballing in Systematic Literature Studies and a Replication in Software Engineering | 2014 | Access |
Wohlin, C.; Mendes, E.; Romero Felizardo, K.; Kalinowski, M. | Guidelines for the Search Strategy to Update Systematic Literature Reviews in Software Engineering | 2020 | Access |
Kitchenham, B.; Budgen, D.; Brereton, P. | Evidence-Based Software Engineering and Systematic Reviews (book) | 2015 | Access |