The Explanation That Hits Home: The Characteristics of Verbal Explanations That Affect Human Perception in Subjective Decision-Making
Bibliographic record
Abstract
Human-AI collaborative decision-making can achieve better outcomes than either party individually. The success of this collaboration can depend on whether the human decision-maker perceives the AI contribution as beneficial to the decision-making process. Beneficial AI explanations are often described as relevant, convincing, and trustworthy. Yet, we know little about the characteristics of explanations that result in these perceptions. Focusing on collaborative subjective decision-making, using the context of subtle sexism, where explanations can surface new interpretations, we conducted a user study (N=20) to explore the structural and content characteristics that affect perceptions of human and AI-generated verbal (text and audio) explanations. We find four groups of characteristics ( Tone, Grammatical Elements, Argumentative Sophistication and Relation to User ), and that the effect of these characteristics on the perception of explanations for subtle sexism depends on the perceived author. Thus, we also identify which explanation characteristics participants use to identify the author of an explanation. Demonstrating the relationship between these characteristics and explanation perceptions, we present a categorized set of characteristics that system builders can leverage to produce the appropriate perception of an explanation for various sensitive contexts. We also highlight human perception biases and associated issues resulting from these perceptions.
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 | 0.005 | 0.071 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".