# RecMind: Japanese Movie Recommendation Dialogue with Seeker's Internal State

arXiv: https://arxiv.org/abs/2402.13522 · HTML: https://mlsanity.com/paper/2402.13522/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 7 of 7)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [Towards Conversational Recommendation over Multi-Type Dialogs](https://mlsanity.com/paper/2005.03954/) (2020)
- [Proactive Human-Machine Conversation with Explicit Conversation Goals](https://mlsanity.com/paper/1906.05572/) (2019)
- [MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks](https://mlsanity.com/paper/2109.06275/) (2021)
- [Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue](https://mlsanity.com/paper/1909.03922/) (2019)

## Abstract (arXiv)

Humans pay careful attention to the interlocutor's internal state in dialogues. For example, in recommendation dialogues, we make recommendations while estimating the seeker's internal state, such as his/her level of knowledge and interest. Since there are no existing annotated resources for the analysis, we constructed RecMind, a Japanese movie recommendation dialogue dataset with annotations of the seeker's internal state at the entity level. Each entity has a subjective label annotated by the seeker and an objective label annotated by the recommender. RecMind also features engaging dialogues with long seeker's utterances, enabling a detailed analysis of the seeker's internal state. Our analysis based on RecMind reveals that entities that the seeker has no knowledge about but has an interest in contribute to recommendation success. We also propose a response generation framework that explicitly considers the seeker's internal state, utilizing the chain-of-thought prompting. The human evaluation results show that our proposed method outperforms the baseline method in both consistency and the success of recommendations.