Dealing with the Challenge of Explainability – A Case Study of Using a Digital Transformation Framework and a Large Language Model Engine to Enhance the Competitive Intelligence Practices of a Small Firm
Bibliographic record
Abstract
There is a lack of research on how users of Large Language Model (LLM) engines actually come up with explanations of their findings in a specific social and organizational context. The issue of LLM explainability is highly relevant in the context of Competitive Intelligence (CI) practices. The objective of this article is to explore how the challenge of dealing with explainability in using LLM tools affects the process and the quality of LLM-driven CI practices and describes a case of using an LLM engine (Perplexity AI) to enhance the CI practices of a small Canadian company. The article emphasizes the need to consider explanation in Generative AI and LLMs as both a construct and an outcome of a socially situated participatory process that incorporates the complex multifaceted relationships between the AI tool, its developers, its users/analysts and their clients. It offers a case study of adopting a digital transformation framework to design a set of prompts enabling comprehensive CI information gathering relevant to the context of a real-life business.
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 | 0.028 | 0.037 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.010 | 0.012 |
| Scholarly communication | 0.007 | 0.008 |
| Open science | 0.003 | 0.007 |
| Research integrity | 0.004 | 0.004 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".