PPPG-DialoGPT: A Prompt-based and Personality-aware Framework For Conversational Recommendation Systems
Bibliographic record
Abstract
Conversational Recommendation Systems (CRSs) are multi-turn dialogue softwares that support recommendation goals. Having a CRS that generates personalized recommen-dations for its users is one of the challenging topics in the recommendation research field. This is due to the diversity of preferences that a user might have within a recommendation session. Recent CRS frameworks are still not really able to effectively provide items of interest to their users, as they do not consider the individuals' personality traits during the recommendation process. These traits are the enduring character-istics and behaviors that comprise a person's unique adjustment and distinguish him from other persons. Thus, considering them during the recommendation process could significantly boost the model performance. In this paper, we propose a personality-aware and prompt-based CRS framework named PPPG-DialoGPT “A Personality and Preference-aware Prompt-based Goal-oriented DialoGPT model”. Our proposed approach aims to benefit from the significant impact that personality traits and prompt-based learning frameworks have on improving the performance of different Natural Language Processing (NLP) and one-shot recommendation tasks. To the best of our knowledge, this paper is the first to employ both individual personality traits and prompts templates during a dialogue-based recommendation session in the field of conversational recommendation system. Experiments and results show that the use of the users' person-ality traits leads to an improvement in the performance of both recommendation and response generation tasks on the movie-based TG- Redial dataset.
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 | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 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".