Large language models for extracting conversational-style explanations for entity matches
Methods, systems, and computer-readable storage media for receiving, by an entity matching ML model, a query and target pair including a query entity and a target entity, providing, by the entity matching ML model, a query-target prediction by processing the query entity and the target entity, the query-target prediction indicating a match type between the query entity and the target entity, generating a prompt by populating a prompt template with at least a portion of the query-target prediction, inputting the prompt into a large language model (LLM), and receiving, from the LLM, an explanation that is responsive to the prompt and that describes one or more reasons for the query-target prediction output by the entity matching ML model.
1 . A computer-implemented method for computer-executed entity matching using one or more machine learning (ML) models, the method being executed by one or more processors and comprising:
receiving, by an entity matching ML model, a query and target pair comprising a query entity and a target entity;
providing, by the entity matching ML model, a query-target prediction by processing the query entity and the target entity, the query-target prediction indicating a match type between the query entity and the target entity;
generating a prompt by populating a prompt template with at least a portion of the query-target prediction, the prompt being generated based on a confidence that is output by the entity matching ML model, the confidence representing a likelihood that the query-target prediction is correct;
inputting the prompt into a large language model (LLM); and
receiving, from the LLM, an explanation that is responsive to the prompt and that describes one or more reasons for the query-target prediction output by the entity matching ML model.
2 . The method of claim 1 , wherein the prompt template comprises placeholders that are populated by a prompt generator using the at least a portion of the query-target prediction.
3 . The method of claim 1 , wherein the prompt is further generated based on a token explanation that is output by the entity matching ML model.
4 . The method of claim 1 , wherein the LLM comprises ChatGPT.
5 . The method of claim 1 , further comprising providing a conversational interface that is operable to display the explanation to a user and receive input from the user to query the LLM.
6 . The method of claim 1 , wherein the match type comprises one of a single match, a multi-match, and no match.
7 . 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 computer-executed entity matching using one or more machine learning (ML) models, the operations comprising:
receiving, by an entity matching ML model, a query and target pair comprising a query entity and a target entity;
providing, by the entity matching ML model, a query-target prediction by processing the query entity and the target entity, the query-target prediction indicating a match type between the query entity and the target entity;
generating a prompt by populating a prompt template with at least a portion of the query-target prediction, the prompt being generated based on a confidence that is output by the entity matching ML model, the confidence representing a likelihood that the query-target prediction is correct;
inputting the prompt into a large language model (LLM); and
receiving, from the LLM, an explanation that is responsive to the prompt and that describes one or more reasons for the query-target prediction output by the entity matching ML model.
8 . The non-transitory computer-readable storage medium of claim 7 , wherein the prompt template comprises placeholders that are populated by a prompt generator using the at least a portion of the query-target prediction.
9 . The non-transitory computer-readable storage medium of claim 7 , wherein the prompt is further generated based on a token explanation that is output by the entity matching ML model.
10 . The non-transitory computer-readable storage medium of claim 7 , wherein the LLM comprises ChatGPT.
11 . The non-transitory computer-readable storage medium of claim 7 , wherein operations further comprise providing a conversational interface that is operable to display the explanation to a user and receive input from the user to query the LLM.
12 . The non-transitory computer-readable storage medium of claim 7 , wherein the match type comprises one of a single match, a multi-match, and no match.
13 . 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 computer-executed entity matching using one or more machine learning (ML) models, the operations comprising:
receiving, by an entity matching ML model, a query and target pair comprising a query entity and a target entity;
providing, by the entity matching ML model, a query-target prediction by processing the query entity and the target entity, the query-target prediction indicating a match type between the query entity and the target entity;
generating a prompt by populating a prompt template with at least a portion of the query-target prediction, the prompt being generated based on a confidence that is output by the entity matching ML model, the confidence representing a likelihood that the query-target prediction is correct;
inputting the prompt into a large language model (LLM); and
receiving, from the LLM, an explanation that is responsive to the prompt and that describes one or more reasons for the query-target prediction output by the entity matching ML model.
14 . The system of claim 13 , wherein the prompt template comprises placeholders that are populated by a prompt generator using the at least a portion of the query-target prediction.
15 . The system of claim 13 , wherein the prompt is further generated based on a token explanation that is output by the entity matching ML model.
16 . The system of claim 13 , wherein the LLM comprises ChatGPT.
17 . The system of claim 13 , wherein operations further comprise providing a conversational interface that is operable to display the explanation to a user and receive input from the user to query the LLM.