An LLM's Attempts to Adapt to Diverse Software Engineers' Problem-Solving Styles: More Inclusive & Equitable?
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910875694137344 |
|---|---|
| author | Anderson, Andrew Piorkowski, David Burnett, Margaret Weisz, Justin |
| author_facet | Anderson, Andrew Piorkowski, David Burnett, Margaret Weisz, Justin |
| contents | Software engineers use code-fluent large language models (LLMs) to help explain unfamiliar code, yet LLM explanations are not adapted to engineers' diverse problem-solving needs. We prompted an LLM to adapt to five problem-solving style types from an inclusive design method, the Gender Inclusiveness Magnifier (GenderMag). We ran a user study with software engineers to examine the impact of explanation adaptations on software engineers' perceptions, both for explanations which matched and mismatched engineers' problem-solving styles. We found that explanations were more frequently beneficial when they matched problem-solving style, but not every matching adaptation was equally beneficial; in some instances, diverse engineers found as much (or more) benefit from mismatched adaptations. Through an equity and inclusivity lens, our work highlights the benefits of having an LLM adapt its explanations to match engineers' diverse problem-solving style values, the potential harms when matched adaptations were not perceived well by engineers, and a comparison of how matching and mismatching LLM adaptations impacted diverse engineers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11018 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An LLM's Attempts to Adapt to Diverse Software Engineers' Problem-Solving Styles: More Inclusive & Equitable? Anderson, Andrew Piorkowski, David Burnett, Margaret Weisz, Justin Human-Computer Interaction Software engineers use code-fluent large language models (LLMs) to help explain unfamiliar code, yet LLM explanations are not adapted to engineers' diverse problem-solving needs. We prompted an LLM to adapt to five problem-solving style types from an inclusive design method, the Gender Inclusiveness Magnifier (GenderMag). We ran a user study with software engineers to examine the impact of explanation adaptations on software engineers' perceptions, both for explanations which matched and mismatched engineers' problem-solving styles. We found that explanations were more frequently beneficial when they matched problem-solving style, but not every matching adaptation was equally beneficial; in some instances, diverse engineers found as much (or more) benefit from mismatched adaptations. Through an equity and inclusivity lens, our work highlights the benefits of having an LLM adapt its explanations to match engineers' diverse problem-solving style values, the potential harms when matched adaptations were not perceived well by engineers, and a comparison of how matching and mismatching LLM adaptations impacted diverse engineers. |
| title | An LLM's Attempts to Adapt to Diverse Software Engineers' Problem-Solving Styles: More Inclusive & Equitable? |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2503.11018 |