8286314 A Large language model for identifying industry-funded research on the carcinogenicity of benzene and cobalt metal
Bibliographic record
Abstract
Objective Industry-funded research is a threat to the validity of scientific inference on carcinogenic hazards. Scientists require tools to better identify industry-funded studies and minimize the influence of industry bias in evidence synthesis reviews. We applied a novel large language model (LLM)-based tool named InfluenceMapper to demonstrate and evaluate its performance in identifying industry sponsored research on the carcinogenicity of two occupational exposures of commercial interest by major industries, benzene and cobalt. Material and Methods We identified all epidemiological, animal bioassay, and mechanistic studies included in systematic reviews on the carcinogenicity of benzene and cobalt conducted by the WHO/IARC Monographs Programme. InfluenceMapper extracted sponsoring entities disclosed in study publications and classified 40 possible relationship types between all entities and the study and each author. A human classified entities as industry or industry-funded. Positive predictive values described the extent of false positive relationships. Results Analyses included 1,520 studies for both agents. We identified 184 disclosed industry or industry-funded entities from InfluenceMapper output that were involved in 453 distinct study-entity and author-entity relationships. For each agent, between 4-8% of studies were funded by industry and 1-4% of studies had at least one author that disclosed receiving industry funding. Industry trade associations funded 19 studies published in 14 journals over a 37-year span. After funding, the most prevalent disclosed relationships with industry were receiving data, holding employment, paid consulting, and providing expert testimony. Industry sponsored research consisted predominantly of mechanistic studies. Positive predictive values were excellent (>98%) for study-entity relationships but declined for relationships with individual authors. Conclusion LLM-based tools can significantly expedite and bolster the detection of industry sponsored research in cancer prevention. Possible use cases include facilitating the assessment of bias from industry studies in evidence synthesis reviews and alerting scientists to the influence of industry on scientific inference about carcinogenic hazards.
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 | 0.014 | 0.065 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.006 |
| Bibliometrics | 0.007 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.028 | 0.004 |
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".