Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.00033 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916269095124992 |
|---|---|
| author | Kemper, Sara Cui, Justin Dicarlantonio, Kai Lin, Kathy Tang, Danjie Korikov, Anton Sanner, Scott |
| author_facet | Kemper, Sara Cui, Justin Dicarlantonio, Kai Lin, Kathy Tang, Danjie Korikov, Anton Sanner, Scott |
| contents | Conversational recommendation (ConvRec) systems must understand rich and diverse natural language (NL) expressions of user preferences and intents, often communicated in an indirect manner (e.g., "I'm watching my weight"). Such complex utterances make retrieving relevant items challenging, especially if only using often incomplete or out-of-date metadata. Fortunately, many domains feature rich item reviews that cover standard metadata categories and offer complex opinions that might match a user's interests (e.g., "classy joint for a date"). However, only recently have large language models (LLMs) let us unlock the commonsense connections between user preference utterances and complex language in user-generated reviews. Further, LLMs enable novel paradigms for semi-structured dialogue state tracking, complex intent and preference understanding, and generating recommendations, explanations, and question answers. We thus introduce a novel technology RA-Rec, a Retrieval-Augmented, LLM-driven dialogue state tracking system for ConvRec, showcased with a video, open source GitHub repository, and interactive Google Colab notebook. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00033 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Tracking Kemper, Sara Cui, Justin Dicarlantonio, Kai Lin, Kathy Tang, Danjie Korikov, Anton Sanner, Scott Computation and Language Artificial Intelligence Conversational recommendation (ConvRec) systems must understand rich and diverse natural language (NL) expressions of user preferences and intents, often communicated in an indirect manner (e.g., "I'm watching my weight"). Such complex utterances make retrieving relevant items challenging, especially if only using often incomplete or out-of-date metadata. Fortunately, many domains feature rich item reviews that cover standard metadata categories and offer complex opinions that might match a user's interests (e.g., "classy joint for a date"). However, only recently have large language models (LLMs) let us unlock the commonsense connections between user preference utterances and complex language in user-generated reviews. Further, LLMs enable novel paradigms for semi-structured dialogue state tracking, complex intent and preference understanding, and generating recommendations, explanations, and question answers. We thus introduce a novel technology RA-Rec, a Retrieval-Augmented, LLM-driven dialogue state tracking system for ConvRec, showcased with a video, open source GitHub repository, and interactive Google Colab notebook. |
| title | Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Tracking |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.00033 |