Information processing apparatus

Abstract

To improve the response accuracy of a large-scale language model. An information processing apparatus includes a reception mechanism capable of receiving a prompt input to a large-scale language model, and a display mechanism that displays a reception image for receiving the prompt, the reception image including a first input field related to a first component that is part of the prompt and a second input field related to a second component that is another part of the prompt. The reception mechanism receives first information and second information input to the first input field and the second input field, respectively, as the prompt.

Description

Technical Field

[0001] This invention relates to the technical field of an information processing device. Background Technology

[0002] As such a device, for example, the following device has been proposed: a language model generates document-based query data, and the pairing of documents and query data is used for learning the retrieval model of a chatbot (see Patent Document 1).

[0003] Patent Document 1: Japanese Patent Application Publication No. 2023-076413 Summary of the Invention

[0004] Chatbots utilizing Large Language Models (LLMs) have been proposed as conversational robots. However, the responses generated by LLMs (in other words, chatbots) are sometimes not the responses requested by the user. Furthermore, LLMs refer to language models built using very large datasets and deep learning techniques.

[0005] The present invention was made in view of the above circumstances, and its object is to provide an information processing device that can improve the response accuracy of large-scale language models.

[0006] An information processing apparatus according to one aspect of the present invention includes: a receiving mechanism capable of receiving a prompt input into a large-scale language model; and a display mechanism displaying a received image for receiving the prompt, the received image including a first input field associated with a first component as part of the prompt and a second input field associated with a second component as another part of the prompt, the receiving mechanism receiving first information and second information respectively input into the first input field and the second input field as the prompt. Attached Figure Description

[0007] Figure 1 This is a block diagram illustrating an example of the structure of an information processing apparatus according to an embodiment.

[0008] Figure 2 This is a diagram representing an example of an image being displayed. Detailed Implementation

[0009] refer to Figure 1 and Figure 2 The implementation methods related to the information processing device will be described. Figure 1The information processing device 10 includes a computing unit 11, a storage unit 12, a communication unit 13, an input unit 14, and an output unit 15. The computing unit 11, storage unit 12, communication unit 13, input unit 14, and output unit 15 are connected via a data bus 16. Furthermore, the information processing device 10 can be a personal computer, a tablet terminal, or a smartphone.

[0010] The arithmetic unit 11 may have a processor. Furthermore, the arithmetic unit 11 may have a single processor or multiple processors. That is, the arithmetic unit 11 may have more than one processor. Additionally, the processor may be a multi-core processor. In the case where the arithmetic unit 11 has a single processor that functions as a multi-core processor, it can be said that the arithmetic unit 11 logically has multiple processors.

[0011] The processor may be at least one of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Field Programmable Gate Array (FPGA), and a Tensor Processing Unit (TPU).

[0012] Storage device 12 may be at least one of random access memory (RAM), read-only memory (ROM), hard disk drive, magneto-optical disk drive, solid-state drive (SSD), and optical disk array. That is, storage device 12 may be implemented by a single device or by multiple devices.

[0013] The communication device 13 can communicate with external devices of the information processing device 10. In addition, the communication device 13 can perform wired communication or wireless communication.

[0014] Input device 14 is a device capable of receiving information input from an external source to information processing device 10. Input device 14 may include user-operable devices of information processing device 10 (e.g., keyboard, mouse, touch panel, etc.). Input device 14 may include, for example, a recording medium reading device capable of reading information recorded on a recording medium removable from information processing device 10, such as a Universal Serial Bus (USB) memory. Furthermore, when information is input to information processing device 10 via communication device 13 (in other words, when information processing device 10 obtains information via communication device 13), communication device 13 may function as an input device.

[0015] Output device 15 is a device capable of outputting information to the outside of information processing device 10. Output device 15 includes a display device 151 capable of outputting visual information such as characters and images. Additionally, output device 15 may include a speaker capable of outputting auditory information such as sound. Output device 15 may include a vibration motor capable of outputting tactile information such as vibration. Output device 15 may include a printer. Output device 15 can output information to recording media removable from information processing device 10, such as a USB memory. Furthermore, when information processing device 10 outputs information via communication device 13, communication device 13 can function as an output device.

[0016] Storage device 12 is capable of storing desired data. The computer program CP executed by the arithmetic unit 11 can be stored in storage device 12. When the arithmetic unit 11 executes the computer program CP, storage device 12 can temporarily store data temporarily used by the arithmetic unit 11.

[0017] Furthermore, the computer program CP can be recorded on a computer-readable and non-temporary recording medium. In this case, the computer program CP can be stored in the storage device 12 by reading the recording medium using a recording medium reading device (not shown) included in the information processing device 10. Additionally, at least one of optical discs, magnetic media, magneto-optical discs, semiconductor memory, and any medium capable of storing other programs can be used as the recording medium. Furthermore, the computer program CP can also be obtained from an external (not shown) device outside the information processing device 10 via the communication device 13. In other words, the computer program CP can be downloaded from an external device to the storage device 12 of the information processing device 10.

[0018] The arithmetic unit 11 (e.g., a processor) can perform the processing to be performed by the information processing unit 10 together with the storage device 12 storing the computer program CP (in other words, together with the storage device 12 and the computer program CP stored in the storage device 12). For example, the arithmetic unit 11 can implement logical function blocks for performing the processing to be performed by the information processing unit 10 within the arithmetic unit 11 (e.g., within the processor) by executing the computer program CP.

[0019] Information processing device 10 can access server 20, which provides chatbot services using Large Scale Language Model (LLM), via network NW. That is, information processing device 10 and server 20 are configured to communicate via network NW. Furthermore, server 20 can be a cloud server. Server 20 can be called an LLM server. Network NW can be a wide area network such as the Internet, or a local area network such as a local area network (LAN). Additionally, information processing device 10 and server 20 can constitute information processing system 1.

[0020] The computer program CP stored in the storage device 12 includes a computer program (hereinafter, appropriately referred to as the "chat application") related to the application for utilizing the chatbot service described above. The user of the information processing device 10 can utilize the chatbot service by launching the chat application via the input device 14.

[0021] For example, a user can enter a question in the input field of a chat application via input device 14. Furthermore, users are not limited to character input; they can also input by voice. A "question" is not limited to interrogative sentences. For example, a "question" can be a sentence containing expressions such as "Please tell me about ****" or "Please answer about ****," which includes requests, instructions, or commands. Therefore, a "question" is not limited to interrogative sentences; it can be a sentence that includes expressions such as requests, instructions, or commands. That is, a "question" can refer to a sentence requesting an answer from the other party.

[0022] The processing unit 11 can send first information representing a question to the server 20 via the communication device 13. Upon receiving the first information, the server 20 can input a prompt including the question represented by the first information into a large-scale language model. The server 20 can obtain an answer to the question generated by the large-scale language model. The server 20 can then send second information representing the answer to the information processing unit 10. Upon receiving the second information, the processing unit 11 of the information processing unit 10 can control the display device 151 to display the answer represented by the second information.

[0023] In addition, the chatbot service mentioned above may be a chatbot service that uses a mechanism (Retrieval-Augmented Generation: RAG) to give a large-scale language model a unique information source by combining the search of a large-scale language model with a specific information source (so-called knowledge base).

[0024] For example, a user can enter a question in the input field of a chat application via input device 14. The processing device 11 can search a knowledge base based on the question. The processing device 11 can send third information representing the question and search results to server 20 via communication device 13. Upon receiving the third information, server 20 can input a prompt including the question and search results represented by the third information into a large-scale language model. Server 20 can obtain an answer to a document generated by the large-scale language model. Server 20 can send fourth information representing the answer to information processing device 10. Upon receiving the fourth information, the processing device 11 of information processing device 10 can control display device 151 to display the answer represented by the fourth information.

[0025] However, the answers generated by large-scale language models are sometimes not the answers the user requests. On the other hand, it is known that the accuracy (or quality) of responses from large-scale language models can be improved by refining the content of the prompts.

[0026] The information processing device 10 involved in this embodiment will Figure 2 Image 210 is displayed on display device 151 as one of the images associated with the chat application. Image 210 includes input fields 211 and 212. Additionally, image 210 may include more than three input fields. For example, a user can create (or add) new input fields by selecting button 213 via input device 14.

[0027] For example, input field 211 could be an input field for a user to enter a question. As mentioned above, a question can be a sentence requesting an answer from the other party (in this case, a large-scale language model). Therefore, at least one of "question," "instruction," and "query" can be entered in input field 211.

[0028] For example, input field 212 can be an input field for components other than the question. Components other than the question can include: "information for specifying the data assigned to the large-scale language model," "output examples for specifying the output format," "templates for specifying the form or structure of the answer," "information for specifying the style of the answer," "information for explicitly specifying the goal or intent of the prompt," "constraints when the large-scale language model generates an answer," "conditions or prerequisites that should be considered when the large-scale language model generates an answer," "explanations of specific terms or concepts (e.g., synonyms)," "information for specifying content that deviates from or excludes general rules," "reference information related to the generated answer," "information that helps in answering (e.g., guidance, notes, supplementary explanations)," "keywords for focusing on a specific topic or content," "information for specifying the steps for generating an answer," "checklists for confirming items or steps," "information for specifying a specific situation or background (e.g., role)," and so on.

[0029] For example, a user can enter information (e.g., a question) in input fields 211 and 212 via input device 14. Figure 2 As shown, an initial value IV can be entered in input field 212. Therefore, the user can leave input field 212 blank. In other words, the user can leave the initial value IV unchanged. For example, as an example of an initial value IV, "I will not answer if I am not confident" can be entered in input field 212. For example, the user can change the initial value of "I will not answer if I am not confident" to "I will answer regardless of confidence".

[0030] After entering information in input fields 211 and 212, the user can select button 214 via input device 14. As a result, processing device 11 receives the information entered into input fields 211 and 212 as a prompt for input into a large-scale language model. Processing device 11 can send the received prompt (equivalent to the first information mentioned above) to server 20 via communication device 13. In addition, the information entered into input field 212 can be an initial value IV. Furthermore, image 210 may include at least one of the prompts and descriptions related to the information to be entered into input fields 211 and 212 respectively.

[0031] (Technical effect)

[0032] Assuming that there is only one input field in a screen related to a chat application, the user is highly likely to only input the question. As a result, the large-scale language model may generate an answer that differs from the user's requested response. In contrast, the image 210 of this embodiment includes at least two input fields 211 and 212. Therefore, image 210 allows the user to notice that information other than the question can be input into the large-scale language model. Moreover, by inputting information other than the question along with the question into the large-scale language model, it is expected that the answer generated by the large-scale language model will be closer to the user's requested response. That is, according to the information processing apparatus 10 of this embodiment, the accuracy of the large-scale language model's response can be improved. Furthermore, when an initial value IV is input in input field 212, the user can input only the question in input field 211 when the user does not need to change the initial value IV. Therefore, the user's burden can be reduced.

[0033] The invention described below is an embodiment derived from the above-described implementation.

[0034] One aspect of the invention relates to an information processing apparatus comprising: a receiving mechanism capable of receiving prompts input into a large-scale language model; and a display mechanism displaying a received image for receiving the prompts, the received image including a first input field associated with a first component as part of the prompt and a second input field associated with a second component as another part of the prompt, the receiving mechanism receiving first information and second information respectively input into the first input field and the second input field as the prompts. In the above embodiment, "processing device 11" is an example of "receiving mechanism," "display device 151" is an example of "display mechanism," and "image 210" is an example of "received image."

[0035] In the information processing device described above, an initial value related to the second component can be entered in the second input field.

[0036] The present invention is not limited to the embodiments described above, and appropriate modifications can be made without departing from the spirit or idea of ​​the invention as read in its entirety from the claims and description. Information processing apparatuses that accompany such modifications are also included within the technical scope of the present invention.

[0037] Symbol Explanation

[0038] 10-Information processing device, 11-Arithmetic processing device, 12-Storage device, 13-Communication device, 14-Input device, 15-Output device, 151-Display device.

Claims

1. An information processing device, characterized in that, have: The receiving mechanism is capable of receiving prompts input into a large-scale language model; and A display mechanism that displays a received image for receiving the prompt. The received image includes a first input field associated with a first component that is part of the prompt and a second input field associated with a second component that is another part of the prompt. The receiving mechanism receives the first information and the second information respectively entered into the first input field and the second input field as the prompt.

2. The information processing device according to claim 1, characterized in that, Enter the initial value related to the second component in the second input field.

Images