Editorial: Explanation in human-AI systems
Bibliographic record
Abstract
The answer to the question "what is a good explanation for lay users" becomes more challenging within a broader, multi-disciplinary context, as the one of our call, from philosophy to sociology, economics and computer sciences. In this context, XAI should entail another level of discussions that need to be addressed: our relationship, as humans, to AI systems, in general. Nonetheless, the term 'explain' derives from the Latin verb 'explanare', which means, literally, 'to make level'. Thus, the discussions and scientific endeavours into XAI could entail the notion of ourselves 'making level' with AI systems, which again brings us to the old question as to our relationship to and with AI systems. More specifically, bringing in our multifaceted cultural notions of AI and human beings, for instance, in terms of master and servant, or who is and will be dominating whom (e.g., Space Odyssey's HAL).Arguably, the intertwined cultural perceptions and (often incorrect, albeit popular) ideas regarding AI and its potentials ultimately also influence lay persons perceived needs for explanation when interacting with AI systems. For example, when interacting with a social robot, ideally, we should not have any perceived need for explanation -or only as much or little as we would have when interacting with any other social, human companion. Given that we are seeing a machine, however, brings up expectations and impressions formed by popular culture, and thus the need for explanation to, maybe, satisfy a need for safety, trust, etc.Therefore, answering the research question "what is a good explanation" is far from obvious. Seeking answers to this research question has been the main incentive for the launch of this research topic.
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 | 0.008 | 0.030 |
| Meta-epidemiology (narrow) | 0.004 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.003 |
| Bibliometrics | 0.006 | 0.002 |
| Science and technology studies | 0.005 | 0.005 |
| Scholarly communication | 0.009 | 0.006 |
| Open science | 0.005 | 0.002 |
| Research integrity | 0.022 | 0.026 |
| Insufficient payload (model declined to judge) | 0.020 | 0.017 |
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".