QUESTION ANSWERING USING ENHANCED RETRIEVAL-AUGMENTED GENERATION
A method of question answering using enhanced retrieval-augmented generation according to an embodiment includes receiving, by a computing system, a user query, pre-processing, by the computing system, the user query to determine whether the user query is associated with malicious intent, retrieving, by the computing system, relevant data from a knowledge base by using a keyword index and a semantic index in response to determining that the user query is not associated with malicious intent, prompting, by the computing system, a large language model to generate an answer to the user query based on only the relevant data retrieved from the knowledge base, and receiving, by the computing system, the answer to the user query from the large language model in response to the prompt.
1 . A method of question answering using enhanced retrieval-augmented generation, the method comprising:
receiving, by a computing system, a user query;
pre-processing, by the computing system, the user query to determine whether the user query is associated with malicious intent;
retrieving, by the computing system, relevant data from a knowledge base by using a keyword index and a semantic index in response to determining that the user query is not associated with malicious intent;
prompting, by the computing system, a large language model to generate an answer to the user query based on only the relevant data retrieved from the knowledge base; and
receiving, by the computing system, the answer to the user query from the large language model in response to the prompt.
2 . The method of claim 1 , wherein pre-processing the user query comprises applying a binary classifier to the user query.
3 . The method of claim 1 , wherein retrieving the relevant data from the knowledge base comprises identifying a set of most relevant data chunks to the user query from the knowledge base using the keyword index.
4 . The method of claim 3 , wherein retrieving the relevant data from the knowledge base comprises:
retrieving embeddings of the set of most relevant data chunks identified using the keyword index; and
re-ranking, using the semantic index, the set of most relevant data chunks based on a respective semantic similarity of each data chunk of the set of most relevant data chunks to a query embedding associated with the user query.
5 . The method of claim 1 , wherein prompting the large language model to generate the answer to the user query comprises prompting the large language model to explicitly output a thought process to generation of the answer.
6 . The method of claim 1 , wherein prompting the large language model to generate the answer to the user query comprises generating answer highlights in the relevant data using a small language model (SLM).
7 . The method of claim 1 , further comprising:
determining, by the computing system, a confidence that the relevant data is responsive to the user query; and
discarding, by the computing system, a first subset of the relevant data in response to determining that the confidence that the first subset of the relevant data is responsive to the user query is below a first predefined threshold.
8 . The method of claim 7 , wherein prompting the large language model to generate the answer to the user query based on only the relevant data retrieved from the knowledge base comprises prompting the large language model to generate the answer to the user query based on only a second subset of the relevant data in response to determining that the confidence that the second subset of the relevant data is responsive to the user query exceeds a second predefined threshold.
9 . The method of claim 1 , further comprising comparing, by the computing system, the answer against the user query to determine a relevancy of the answer to the user query.
10 . The method of claim 1 , further comprising comparing, by the computing system, the answer against the relevant data to determine whether the answer was generated solely based on the relevant data.
11 . The method of claim 1 , further comprising processing, by the computing system, the answer to determine whether an output format or encoding of the answer has been manipulated.
12 . The method of claim 1 , further comprising applying, by the computing system, at least one of a word-based filter or a topic-based filter to the answer to detect and remove objectionable content from the answer.
13 . A computing system for question answering using enhanced retrieval-augmented generation, the computing system comprising:
at least one processor; and
at least one memory having a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the computing system to:
receive a user query;
pre-process the user query to determine whether the user query is associated with malicious intent;
retrieve relevant data from a knowledge base by using a keyword index and a semantic index in response to a determination that the user query is not associated with malicious intent;
prompt a large language model to generate an answer to the user query based on only the relevant data retrieved from the knowledge base; and
receive the answer to the user query from the large language model in response to the prompt.
14 . The computing system of claim 13 , wherein to pre-process the user query comprises to apply a binary classifier to the user query.
15 . The computing system of claim 13 , wherein to retrieve the relevant data from the knowledge base comprises to identify a set of most relevant data chunks to the user query from the knowledge base using the keyword index.
16 . The computing system of claim 15 , wherein to retrieve the relevant data from the knowledge base comprises to:
retrieve embeddings of the set of most relevant data chunks identified using the keyword index; and
re-rank, using the semantic index, the set of most relevant data chunks based on a respective semantic similarity of each data chunk of the set of most relevant data chunks to a query embedding associated with the user query.
17 . The computing system of claim 13 , wherein to prompt the large language model to generate the answer to the user query comprises to prompt the large language model to explicitly output a thought process to generation of the answer.
18 . The computing system of claim 13 , wherein to prompt the large language model to generate the answer to the user query comprises to generate answer highlights in the relevant data using a small language model (SLM).
19 . The computing system of claim 13 , wherein the plurality of instructions further causes the computing system to:
determine a confidence that the relevant data is responsive to the user query; and
discard a first subset of the relevant data in response to a determination that the confidence that the first subset of the relevant data is responsive to the user query is below a first predefined threshold.
20 . The computing system of claim 19 , wherein to prompt the large language model to generate the answer to the user query based on only the relevant data retrieved from the knowledge base comprises to prompt the large language model to generate the answer to the user query based on only a second subset of the relevant data in response to a determination that the confidence that the second subset of the relevant data is responsive to the user query exceeds a second predefined threshold.