Leveraging large language models in content-based recommendation systems

A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for providing recommendations from a computer-implemented recommendation system using a large language model (LLM), the operations comprising:

• during a pre-production stage:
• generating a set of prompts using a sub-set of items of a set of items available to users;
• prompting the LLM using the set of prompts, the LLM returning a set of virtual items, each virtual item being responsive to a prompt in the set of prompts, the virtual item being included in the set of virtual items;
• creating a map using the sub-set of items and the set of virtual items;
• subsequent to the pre-production stage:
• receiving first interaction data representative of a first item a user has interacted with, the first item being included in the set of items available to users;
• generating a first set of recommended items through content-based collaborative filtering using the first item;
• determining that the first set of recommended items comprises a virtual item that had been generated by the LLM during the pre-production stage, the virtual item comprising a fictional item that is unavailable, and in response:
• determining an item from the map using the virtual item as an index, the map mapping items to virtual items generated by the LLM and being generated during the pre-production stage, and
• replacing the virtual item with the item in the first set of recommended items to provide a modified set of recommended items;
• transmitting first item data representative of the modified set of recommended items to display items in the modified set of recommended items to the user;
• receiving second interaction data representative of a second item a user has interacted with;
• generating a second set of recommended items through content-based collaborative filtering using the second item;
• and
• determining that the second set of recommended items is absent any virtual items, and in response:
• transmitting second item data representative of the second set of recommended items to display items in the second set of recommended items.

A system, comprising:

• a computing device;
• and
• a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for providing recommendations from a computer-implemented recommendation system using a large language model (LLM), the operations comprising:
• during a pre-production stage:
• generating a set of prompts using a sub-set of items of a set of items available to users;
• prompting the LLM using the set of prompts, the LLM returning a set of virtual items, each virtual item being responsive to a prompt in the set of prompts, the virtual item being included in the set of virtual items;
• creating a map using the sub-set of items and the set of virtual items;
• subsequent to the pre-production stage:
• receiving first interaction data representative of a first item a user has interacted with, the first item being included in the set of items available to users;
• generating a first set of recommended items through content-based collaborative filtering using the first item;
• determining that the first set of recommended items comprises a virtual item that had been generated by the LLM during the pre-production stage, the virtual item comprising a fictional item that is unavailable, and in response:
• determining an item from the map using the virtual item as an index, the map mapping items to virtual items generated by the LLM and being generated during the pre-production stage, and
• replacing the virtual item with the item in the first set of recommended items to provide a modified set of recommended items;
• transmitting first item data representative of the modified set of recommended items to display items in the modified set of recommended items to the user;
• receiving second interaction data representative of a second item a user has interacted with;
• generating a second set of recommended items through content-based collaborative filtering using the second item;
• and
• determining that the second set of recommended items is absent any virtual items, and in response:
• transmitting second item data representative of the second set of recommended items to display items in the second set of recommended items.