Mixing It Up: Inducing Empathy and Politeness using Multiple Behaviour-aware Generators for Conversational Systems
Bibliographic record
Abstract
Politeness is a key component that can assist in building a strong customer-agent relationship.With the ongoing increase in customer-care systems, it is crucial to have healthy relations with the users providing satisfaction and a better customer experience.In this regard, it is significant to model the different polite behaviors in an agent to help the user in reaching the intended objectives.In our current work, we propose the task of polite behavior-aware generation considering the affective state of the user and the conversational context.We design a Transformer based encoder-decoder framework with three major components i.e., Affective tracker, Behaviour-aware generators, and Polite generator.The affective tracker is a context encoder that captures the contextual information along with the affective information in the utterances; the behavior-aware generators independently attends to the context information to compute behavior-aware polite representations and finally, polite generator generates the final polite response considering the representations from different generators.Experimental results on the CYCCD dataset prove that our approach generates contextually correct and relevant responses compared to the state-of-the-art approaches and the baselines.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".