MétaCan
Menu
Back to cohort
Record W4414398162 · doi:10.33137/codex.v1i1.45679

Building an Emphatic AI Coach & Agent

2025· article· en· W4414398162 on OpenAlexaff
Dev Vora, Dev Shah, Tanish Roy, Mehtab Cheema, Saadullah Shahzad

Bibliographic record

VenueJournal of Computing Data and Exploration · 2025
Typearticle
Languageen
FieldComputer Science
TopicSoftware Engineering Techniques and Practices
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsPipeline (software)Ask priceConversationApplications of artificial intelligenceChatbot

Abstract

fetched live from OpenAlex

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.871
Threshold uncertainty score0.360

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.003
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.076
GPT teacher head0.378
Teacher spread0.301 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Computing Data and ExplorationSame topicSoftware Engineering Techniques and PracticesFrench-language works237,207