A Framework for Soliciting Clarification from Users During Plan Recognition
Bibliographic record
Abstract
In previous work, we used plan recognition to improve responses to users in an advice-giving setting. We then characterized when it was worthwhile to engage a user in clarification dialogue--the cases where plan ambiguity mattered to the formulation of a response. Our current research develops detailed algorithms for selecting what to say during the clarification dialogue. We propose a default strategy for selecting a clarifying question, together with a variety of options to reduce the length of the clarification dialogue. Each clarifying question is introduced in order to prune the set of possible plans. But the system will never overcommit in recognizing the user's plan and thus will never have to backtrack into a debugging dialogue with the user. In all, we now have a more precise formulation for what to say during clarification dialogues, and valuable characterizations of decisions which an advice-giving system must make in generating a dialogue with a user.
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 | 0.020 | 0.034 |
| Meta-epidemiology (narrow) | 0.003 | 0.003 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.004 | 0.001 |
| Science and technology studies | 0.003 | 0.009 |
| Scholarly communication | 0.009 | 0.011 |
| Open science | 0.007 | 0.006 |
| Research integrity | 0.006 | 0.006 |
| Insufficient payload (model declined to judge) | 0.016 | 0.007 |
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".