Building an Emphatic AI Coach & Agent
Bibliographic record
Abstract
Traditional AI models, including ChatGPT, primarily respond with verbose answers rather than engaging in natural, interactive conversations. Human dialogue thrives on clarification—asking the right questions to refine understanding—yet current AI systems leave the burden of re-prompting on the user. Our project aims to shift AI towards a more open and empathic approach by training models to ask clarifying questions rather than merely generating responses. To achieve this, we have built a pipeline of models that assess ambiguity, intent, and sentiment in user queries. These outputs, alongside the original prompt, are processed by an AI agent that determines whether a clarifying question is necessary before generating a response. This approach fosters steerable AI behavior, making models more agentic, adaptable, and human-like in conversation. By developing a dataset of high-quality clarifying questions—both synthetically generated and human-validated—we pave the way for next-generation AI assistants that actively seek to understand user intent rather than passively respond. This project has implications for instruction tuning, AI alignment, and conversational AI, ultimately making models more effective collaborators in human-AI interactions
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.003 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".