Information processing device

Abstract

To improve the response accuracy of large-scale language models. [Solution] The information processing device (10) includes a receiving means (11) capable of receiving prompts input to a large-scale language model, and a display means (151) for displaying a receiving image for receiving prompts. The receiving image includes a first input field relating to a first component which is part of the prompt, and a second input field relating to a second component which is another part of the prompt. The receiving means receives the first information and the second information input into the first input field and the second input field, respectively, as a prompt.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing apparatuses.

Background Art

[0002] As this type of apparatus, for example, an apparatus has been proposed that generates query data based on a document for a language model and uses a pair of the document and the query data for learning a search model for a chatbot (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] As a chatbot, a chatbot using a large language model (LLM) has been proposed. By the way, the answer generated by the large language model (or rather, the chatbot) may not be the answer that the user is seeking. Note that the large language model is a language model constructed using a very large dataset and deep learning technology.

[0005] The present invention has been made in view of the above circumstances, and an object thereof is to provide an information processing apparatus capable of improving the answer accuracy of a large language model.

Means for Solving the Problems

[0006] An information processing device according to one aspect of the present invention comprises a receiving means capable of receiving a prompt input to a large-scale language model, and a display means for displaying a receiving image for receiving the prompt, wherein the receiving image includes a first input field relating to a first component which is part of the prompt, and a second input field relating to a second component which is another part of the prompt, and the receiving means receives first information and second information input to the first input field and the second input field, respectively, as the prompt. [Brief explanation of the drawing]

[0007] [Figure 1] This block diagram shows an example of the configuration of an information processing device according to the embodiment. [Figure 2] This figure shows an example of a displayed image. [Modes for carrying out the invention]

[0008] Embodiments relating to the information processing device will be described with reference to Figures 1 and 2. In Figure 1, the information processing device 10 comprises an arithmetic unit 11, a storage device 12, a communication device 13, an input device 14, and an output device 15. The arithmetic unit 11, storage device 12, communication device 13, input device 14, and output device 15 are connected via a data bus 16. The information processing device 10 may be a personal computer, a tablet terminal, or a smartphone.

[0009] The arithmetic unit 11 may have a processor. The arithmetic unit 11 may have a single processor or multiple processors. In other words, the arithmetic unit 11 may have one or more processors. Furthermore, the processor may be a multi-core processor. If the arithmetic unit 11 has a single processor that is a multi-core processor, then logically, the arithmetic unit 11 can be said to have multiple processors.

[0010] The processor may be at least one of the following: CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), and TPU (Tensor Processing Unit).

[0011] The storage device 12 may be at least one of the following: RAM (Random Access Memory), ROM (Read Only Memory), hard disk drive, magneto-optical disk drive, SSD (Solid State Drive), and optical disk array. In other words, the storage device 12 may be implemented by a single device or by multiple devices.

[0012] The communication device 13 may be capable of communicating with devices outside the information processing device 10. The communication device 13 may use either wired or wireless communication.

[0013] The input device 14 is a device capable of receiving information input to the information processing device 10 from an external source. The input device 14 may include an operating device (e.g., a keyboard, mouse, touch panel, etc.) that can be operated by the user of the information processing device 10. The input device 14 may include a recording medium reader capable of reading information recorded on a recording medium that can be attached to and detached from the information processing device 10, such as a USB (Universal Serial Bus) memory. When information is input to the information processing device 10 via the communication device 13 (in other words, when the information processing device 10 acquires information via the communication device 13), the communication device 13 may function as an input device.

[0014] The output device 15 is a device capable of outputting information to the outside of the information processing device 10. The output device 15 has a display device 151 capable of outputting visual information such as characters and images as the above information. The output device 15 may also have a speaker capable of outputting auditory information such as sound as the above information. The output device 15 may also have a vibration motor capable of outputting tactile information such as vibration as the above information. The output device 15 may also have a printer. The output device 15 may be capable of outputting information to a recording medium that can be attached to and detached from the information processing device 10, such as a USB memory stick. When the information processing device 10 outputs information via the communication device 13, the communication device 13 may function as an output device.

[0015] The storage device 12 is capable of storing desired data. The storage device 12 may store the computer program CP that the arithmetic unit 11 will execute. The storage device 12 may temporarily store data that the arithmetic unit 11 will use temporarily when the arithmetic unit 11 is executing the computer program CP.

[0016] Furthermore, the computer program CP may be recorded on a non-temporary recording medium that is readable by a computer. In this case, the computer program CP may be stored in the storage device 12 by reading the recording medium using a recording medium reading device (not shown) provided by the information processing device 10. Furthermore, at least one of the following may be used as the recording medium: an optical disc, a magnetic medium, a magneto-optical disc, a semiconductor memory, and any other medium capable of storing a program. Furthermore, the computer program CP may be obtained from an external device (not shown) of the information processing device 10 via a communication device 13. In other words, the computer program CP may be downloaded from an external device to the storage device 12 of the information processing device 10.

[0017] The arithmetic unit 11 (for example, a processor) may execute the processing that the information processing device 10 should perform together with the memory device 12 in which the computer program CP is stored (in other words, together with the memory device 12 and the computer program CP stored in the memory device 12). For example, by the arithmetic unit 11 executing the computer program CP, a logical functional block for executing the processing that the information processing device 10 should perform may be realized within the arithmetic unit 11 (for example, within the processor).

[0018] The information processing device 10 can access the server 20, which provides a chatbot service using a large-scale language model (LLM), via a network NW. In other words, the information processing device 10 and the server 20 are configured to communicate with each other via the network NW. The server 20 may be a cloud server. The server 20 may also be referred to as an LLM server. The network NW may be a wide-area network such as the Internet, or a narrow-area network such as a LAN (Local Area Network). The information processing device 10 and the server 20 may constitute an information processing system 1.

[0019] The computer program CP stored in the storage device 12 includes a computer program related to an application for using the chatbot service (hereinafter referred to as the "chat application" as appropriate). By launching the chat application via the input device 14, the user of the information processing device 10 can use the chatbot service.

[0020] For example, the user may input a question sentence into the input field of the chat application via the input device 14. Note that the user may perform voice input, not limited to character input. The "question sentence" is not limited to an interrogative sentence. For example, the "question sentence" may be a sentence including expressions such as "Tell me about ****" or "Answer ****", including requests, instructions, commands, etc. Therefore, the "question sentence" is not limited to a sentence in an interrogative form, but is a concept including sentences including expressions such as requests, instructions, commands, etc. That is, the "question sentence" may mean a sentence asking for an answer from the other party.

[0021] The arithmetic unit 11 may transmit the first information indicating the question sentence to the server 20 via the communication device 13. The server 20 that has received the first information may input a prompt including the question sentence indicated by the first information into the large language model. The server 20 may obtain an answer to the question sentence generated by the large language model. The server 20 may transmit the second information indicating the answer to the information processing device 10. The arithmetic unit 11 of the information processing device 10 that has received the second information may control the display device 151 to display the answer indicated by the second information.

[0022] Note that the above chatbot service may be a chatbot service using a mechanism (Retrieval-Augmented Genration: RAG) that combines a large language model and the search of a specific information source (so-called knowledge base) to provide the large language model with an exclusive information source.

[0023] For example, the user may input a question sentence into the input field of the chat application via the input device 14. The arithmetic unit 11 may search the knowledge base based on the question sentence. The arithmetic unit 11 may transmit, via the communication device 13, third information indicating the question sentence and the search result to the server 20. The server 20 that has received the third information may input a prompt including the question sentence and the search result indicated by the third information into the large language model. The server 20 may acquire an answer to the document generated by the large language model. The server 20 may transmit fourth information indicating the answer to the information processing device 10. The arithmetic unit 11 of the information processing device 10 that has received the fourth information may control the display device 151 to display the answer indicated by the fourth information.

[0024] By the way, the answer generated by the large language model may not be the answer that the user seeks. On the other hand, it is known that by devising the content of the prompt, the answer accuracy (or answer quality) of the large language model can be improved.

[0025] The information processing device 10 according to the present embodiment displays, on the display device 151, an image 210 shown in FIG. 2 as one of the images related to the chat application. The image 210 includes input fields 211 and 212. Note that the image 210 may include three or more input fields. For example, when the user selects the button 213 via the input device 14, a new input field may be generated (or added).

[0026] For example, the input field 211 may be an input field for the user to input a question sentence. As described above, the question sentence may mean a sentence for seeking an answer from the other party (here, the large language model). Therefore, at least one of "question", "instruction", and "query" may be input into the input field 211.

[0027] For example, input field 212 may be an input field where components other than the question text are entered. For example, components other than the question text may include: "information to specify the data to be given to the large language model," "output examples to specify the output format of the answer," "templates to specify the format and structure of the answer," "information to specify the style of the answer," "information to clearly specify the goal and intent of the prompt," "constraints on when the large language model generates the answer," "conditions or assumptions that the large language model should consider when generating the answer," "explanations of specific terms or concepts (e.g., synonyms, etc.)," ​​"information to specify content that deviates from or is excluded from general rules," "reference information related to the generated answer," "information to help answer (e.g., hints, notes, supplementary explanations, etc.)," ​​"keywords to focus on a specific topic or content," "information to specify the procedure for generating the answer," "checklists to verify items and steps," "information to specify a specific situation or background (e.g., role)," etc.

[0028] For example, the user may input information (e.g., a question) into input fields 211 and 212 via the input device 14. As shown in Figure 2, an initial value IV may be entered in input field 212. Therefore, the user does not need to input information into input field 212. In other words, the user does not need to change the initial value IV. For example, "Do not answer if you are not confident" may be entered in input field 212 as an example of an initial value IV. For example, the user may change the initial value "Do not answer if you are not confident" to "Answer regardless of confidence".

[0029] After information is entered into input fields 211 and 212, the user may select button 214 via input device 14. As a result, the arithmetic unit 11 receives the information entered into input fields 211 and 212 as prompts to be input to the large-scale language model. The arithmetic unit 11 may send the received prompts (corresponding to the first information described above) to the server 20 via communication device 13. The information entered into input field 212 may be the initial value IV. Image 210 may include at least one of the suggestions and explanations regarding the information to be entered into input fields 211 and 212, respectively.

[0030] (Technical effects) If a chat application screen has only one input field, users are likely to only enter a question. As a result, the large-scale language model may generate an answer that differs from the answer the user is seeking. In contrast, screen 210 according to this embodiment includes at least two input fields 211 and 212. Therefore, screen 210 can make the user aware that they can input information other than the question into the large-scale language model. When information other than the question is input into the large-scale language model along with the question, it can be expected that the answer generated by the large-scale language model will come closer to the answer the user is seeking. In other words, the information processing device 10 according to this embodiment can improve the accuracy of the answer from the large-scale language model. In addition, if an initial value IV is entered in input field 212 and the user does not need to change the initial value IV, the user may only enter a question in input field 211. Therefore, the burden on the user can be reduced.

[0031] The embodiments of the invention derived from the above-described embodiments are described below.

[0032] An information processing device according to one aspect of the invention includes a receiving means capable of receiving a prompt input to a large-scale language model, and a display means for displaying a receiving image for receiving the prompt, wherein the receiving image includes a first input field relating to a first component which is part of the prompt, and a second input field relating to a second component which is another part of the prompt, and the receiving means receives the first information and the second information input to the first input field and the second input field, respectively, as the prompt. In the above embodiment, the "arithmetic unit 11" corresponds to an example of the "receiving means," the "display device 151" corresponds to an example of the "display means," and the "image 210" corresponds to an example of the "receiving image."

[0033] In the information processing device according to the above embodiment, the second input field may contain an initial value related to the second component.

[0034] The present invention is not limited to the embodiments described above, and can be modified as appropriate without contradicting the gist or idea of ​​the invention as can be read from the claims and specification as a whole. Information processing devices that involve such modifications are also included within the technical scope of the present invention. [Explanation of symbols]

[0035] 10... Information processing device, 11... Arithmetic unit, 12... Memory device, 13... Communication device, 14... Input device, 15... Output device, 151... Display device

Claims

1. A means of receiving prompts that are input to a large-scale language model, A display means for displaying a reception image for accepting the aforementioned prompt, Equipped with, The reception image includes a first input field relating to a first component which is part of the prompt, and a second input field relating to a second component which is another part of the prompt. The receiving means receives the first information and the second information entered in the first input field and the second input field, respectively, as the prompt. Information processing device.

2. The second input field contains the initial value related to the second component. The information processing apparatus according to claim 1.

Images