-
公开(公告)号：US11989527B2
公开(公告)日：2024-05-21
申请号：US18301560
申请日：2023-04-17
Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
Inventor： William Tunstall-Pedoe , Robert Heywood , Seth Warren , Paul Benn , Duncan Reynolds , Ayush Shah , Luci Krnic , Ziyi Zhu
Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.
-
公开(公告)号：US11989507B2
公开(公告)日：2024-05-21
申请号：US18301615
申请日：2023-04-17
Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
Inventor： William Tunstall-Pedoe , Robert Heywood , Seth Warren , Paul Benn , Duncan Reynolds , Ayush Shah , Luci Krnic , Ziyi Zhu
CPC classification number: G06F40/20 , G06F16/3344 , G06F40/56
Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.
-
Patent Agency Ranking
公开(公告)号：US12164868B2
公开(公告)日：2024-12-10
申请号：US18648788
申请日：2024-04-29
Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
Inventor： William Tunstall-Pedoe , Robert Heywood , Seth Warren , Paul Benn , Duncan Reynolds , Ayush Shah , Luci Krnic , Ziyi Zhu
Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.
-
公开(公告)号：US12067362B2
公开(公告)日：2024-08-20
申请号：US18301573
申请日：2023-04-17
Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
Inventor： William Tunstall-Pedoe , Robert Heywood , Seth Warren , Paul Benn , Duncan Reynolds , Ayush Shah , Luci Krnic , Ziyi Zhu
IPC: G06F40/279 , G06F40/40
CPC classification number: G06F40/279 , G06F40/40
Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.
-
公开(公告)号：US12073180B2
公开(公告)日：2024-08-27
申请号：US18301594
申请日：2023-04-17
Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
Inventor： William Tunstall-Pedoe , Robert Heywood , Seth Warren , Paul Benn , Duncan Reynolds , Ayush Shah , Luci Krnic , Ziyi Zhu
IPC: G06F40/279
CPC classification number: G06F40/279
Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.
-
公开(公告)号：US12008333B2
公开(公告)日：2024-06-11
申请号：US18515488
申请日：2023-11-21
Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
Inventor： William Tunstall-Pedoe , Robert Heywood , Seth Warren , Paul Benn , Duncan Reynolds , Ayush Shah , Luci Krnic , Ziyi Zhu
IPC: G06F17/00 , G06F40/205 , G06F40/30 , G06F40/56
CPC classification number: G06F40/56 , G06F40/205 , G06F40/30
Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.
-
公开(公告)号：US11977854B2
公开(公告)日：2024-05-07
申请号：US18301639
申请日：2023-04-17
Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
Inventor： William Tunstall-Pedoe , Robert Heywood , Seth Warren , Paul Benn , Duncan Reynolds , Ayush Shah , Luci Krnic , Ziyi Zhu
IPC: G06F17/00 , G06F40/205 , G06F40/30 , G06F40/56
CPC classification number: G06F40/56 , G06F40/205 , G06F40/30
Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.
-
-
-
-
-
-
Search Results
7
records
(took 0.036 seconds)
