Will ChatGPT’s Free Language Editing Service Level the Playing Field in Science Communication?: Insights from a Collaborative Project with Non-native English Scholars
Bibliographic record
Abstract
ChatGPT has been widely heralded as a way to level the playing field in scientific communication through its free language editing service. However, such claims lack systematic evidence. A writing scholar (LL) and six non-native English scholars researching health professions education collaborated on this Writer's Craft to fill this gap. Our overarching aim was to provide experiential evidence about ChatGPT's performance as a language editor and writing coach. We implemented three cycles of a systematic procedure, describing how we developed our prompts, selected text for editing, incrementally prompted to refine ChatGPT's responses, and analyzed the quality of its language edits and explanations. From this experience, we offer five insights, and we conclude that the optimism about ChatGPT's capacity to level the playing field for non-native English writers should be tempered. In the writer's craft section we offer simple tips to improve your writing in one of three areas: Energy, Clarity and Persuasiveness. Each entry focuses on a key writing feature or strategy, illustrates how it commonly goes wrong, teaches the grammatical underpinnings necessary to understand it and offers suggestions to wield it effectively. We encourage readers to share comments on or suggestions for this section on Twitter, using the hashtag: #how'syourwriting?
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.031 | 0.090 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.013 | 0.015 |
| Scholarly communication | 0.011 | 0.008 |
| Open science | 0.002 | 0.009 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".