LLM prompt with decoy categories
In one embodiment, a device includes a processor configured to execute a software application to populate a large language model (LLM) prompt template yielding a populated LLM prompt including a categorical question for an LLM to perform a categorization task, the categorical question including given categories and decoy categories, provide the populated LLM prompt as input to the LLM, and receive a text response from the LLM based on processing the populated LLM prompt as input, the text response of the LLM including a categorical answer indicating one of the given categories or one of the decoy categories, and a memory to store data used by the processor.
1 . A device, comprising:
a processor configured to execute a software application to:
populate a large language model (LLM) prompt template yielding a populated LLM prompt including a categorical question for an LLM to perform a categorization task, the categorical question including given categories and decoy categories;
provide the populated LLM prompt as input to the LLM; and
receive a text response from the LLM based on processing the populated LLM prompt as input, the text response of the LLM including a categorical answer indicating one of the given categories or one of the decoy categories; and
a memory to store data used by the processor.
2 . The device according to claim 1 , wherein the software application is configured to:
perform a category-specific operation based on any one of the given categories being selected by the LLM; and
not perform a category-specific operation based on any one of the decoy categories being selected by the LLM.
3 . The device according to claim 1 , wherein inclusion of the decoy categories in the populated LLM prompt causes the LLM to avoid spuriously selecting one of the given categories.
4 . The device according to claim 1 , wherein:
the given categories are categories that are supported by the software application; and
the decoy categories are categories that are unsupported by the software application.
5 . The device according to claim 4 , wherein the software application is configured to respond indicating that a request is unsupported based on any one of the decoy categories being included in the text response of the LLM.
6 . The device according to claim 4 , wherein the software application is configured to respond indicating that a language of a request is unsupported based on any one of the decoy categories being included in the text response of the LLM.
7 . The device according to claim 4 , wherein the given categories are languages that are supported by the software application and the decoy categories are languages that are unsupported by the software application.
8 . The device according to claim 4 , wherein:
the given categories are supported Application Programming Interfaces (APIs); and
the decoy categories are unsupported APIs.
9 . The device according to claim 8 , wherein:
the categorical answer indicates one of the given categories of a given API of the supported APIs; and
the software application is configured to call the given API.
10 . A method, comprising:
populating a large language model (LLM) prompt template yielding a populated LLM prompt including a categorical question for an LLM to perform a categorization task, the categorical question including given categories and decoy categories;
providing the populated LLM prompt as input to the LLM; and
receiving a text response from the LLM based on processing the populated LLM prompt as input, the text response of the LLM including a categorical answer indicating one of the given categories or one of the decoy categories.
11 . The method according to claim 10 , further comprising:
performing a category-specific operation based on any one of the given categories being selected by the LLM; and
not performing a category-specific operation based on any one of the decoy categories being selected by the LLM.
12 . The method according to claim 10 , wherein inclusion of the decoy categories in the populated LLM prompt causes the LLM to avoid spuriously selecting one of the given categories.
13 . The method according to claim 10 , wherein:
the given categories are categories that are supported by a software application; and
the decoy categories are categories that are unsupported by the software application.
14 . The method according to claim 13 , further comprising responding indicating that a request is unsupported based on any one of the decoy categories being included in the text response of the LLM.
15 . The method according to claim 13 , further comprising responding indicating that a language of a request is unsupported based on any one of the decoy categories being included in the text response of the LLM.
16 . The method according to claim 13 , wherein the given categories are languages that are supported by the software application and the decoy categories are languages that are unsupported by the software application.
17 . The method according to claim 13 , wherein:
the given categories are supported Application Programming Interfaces (APIs); and
the decoy categories are unsupported APIs.
18 . The method according to claim 17 , wherein the categorical answer indicates one of the given categories of a given API of the supported APIs, the method further comprising calling the given API.
19 . A software product, comprising a non-transient computer-readable medium in which program instructions are stored, which instructions, when read by a central processing unit (CPU), cause the CPU to:
populate a large language model (LLM) prompt template yielding a populated LLM prompt including a categorical question for an LLM to perform a categorization task, the categorical question including given categories and decoy categories;
provide the populated LLM prompt as input to the LLM; and
receive a text response from the LLM based on processing the populated LLM prompt as input, the text response of the LLM including a categorical answer indicating one of the given categories or one of the decoy categories.