DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Interpretation
As per Claim 5:
“the assignments” in line 2 of claim 5 is interpreted as having antecedent basis from “all unknowns are assigned values” (where each assignment of a value to an unknown is one of “the assignments” in line 2 of claim 5).
As per Claim 8:
“the output” in line 3 of claim 8 is interpreted as referring to “an output” in line 2 of claim 8 (not to any of “the outputs of the LLM” in line 7 of claim 1).
As per Claim 13:
“their” in line 2 of claim 13 is interpreted as referring to “multiple tools” in line 1 of claim 13.
Claim Objections
Claims 4, 8, 10, 11, 13, 17, 20, 22, 23, and 24, are objected to because of the following informalities:
As per Claim 4 (and similarly claim 8, 10, 11, 13, 17, 20, 22, 23, and 24):
“the non LLM engine or tool” in lines 1-2 of claim 4 should be –the non-LLM engine or tool—(i.e. add a hyphen between “non” and “LLM”) for language consistency.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
For clarity of the record, NO new matter rejections are required for claims 1, 29, and 30 because the original Specification of Parent Application 18/301,615 describes “In other examples, continuations generated by the LLM can be translated into UL using the techniques described herein and the UL validated for factual inaccuracies or other contradictions. Where such problems are found, an alternative continuation not including the factual inaccuracy could be generated by the LLM or by the UL (or similar) system before being displayed to the user. Alternatively the incorrect assertion could be removed from the language displayed to the user. In some examples, partial continuations (translations before the LLM has stopped generating) can be translated into UL and a system as described herein can override the continuation when it detects an inconsistency, factual error or other text that can be improved. By replacing or editing the continuation with the improved text, the LLM can then pick up with a context that no longer includes its inferior first response, possibly resulting in a better continuation and with a better overall response” and “An aim of UL is in principle to be able to represent anything expressible in any natural language. An additional aim is for anything expressed in natural language to thus be translatable into UL” (where translation from natural language into UL suggests that UL is not natural language, where UL representations being “fully processable and understandable by automated systems” suggests that UL is “readable” by systems/”machines”, where “validation” of UL can be interpreted as a form of “verification” that operates using UL).
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 6, 7, 10-15, and 17-26 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
The original Specification (i.e. the original Specification of Parent Application 18/301,615, hereafter original Specification, where this application is a continuation, and not a continuation-in-part) does not have written description for the following:
It is not clear where the original Specification supports the limitations of claims 6, 7, 10-15, 17-26.
The dependent claims include the issues of their respective parent claims.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-30 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
As per Claim 1 (and similarly claims 29-30):
“the outputs of the LLM” in line 7 of claim 1 lacks antecedent basis.
“the LLM” in line 7 of claim 1 lacks antecedent basis (lines 2-3 recite “LLM…based system” but claim 1 does not explicitly recite “an LLM”)
Additionally, as per Claim 30:
“the output or response of the LLM-based system to that prompt or question” in the last 2 lines of claim 30 lacks antecedent basis.
As per Claim 2 (and similarly claims 9, 10, 18, ):
“the LLM output” in line 2 of claim 2 is ambiguous (claim 1 recites “the outputs” [plural] “of the LLM” and it is not clear which of the multiple outputs is the one that “the LLM output” in line 2 of claim 2 is supposed to refer to).
As per Claim 11:
“the questions, answers, and verification outcomes” in line 2 of claim 11 lacks antecedent basis.
As per Claim 26:
“the sequence of reasoning steps” in line 2 of claim 26 is ambiguous (line 2 of claim 25 recites “a sequence of reasoning steps” and line 4 of claim 1 also recites “a sequence of reasoning steps”, and so the two recitations do not necessarily refer to the same sequence of reasoning steps, and it is not clear which sequence is the one that “the sequence of reasoning steps” in line 2 of claim 26 when the two recitations refer to different sequences)
As per Claim 27:
“the LLM” in line 2 of claim 27 lacks antecedent basis (as a consequence of “the LLM” in line 7 of claim 1 lacking antecedent basis)
The dependent claims include the issues of their respective parent claims.
Allowable Subject Matter
Claims 1, 29, and 30, would be allowable if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action.
Claims 2-5, 8-9, 16, and 27-30, would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
As per Claim(s) 1 (and similarly claim[s] 29-30, and consequently claim[s] 2-28 which depend on claim[s] 1), the prior art of record does not teach or suggest the combination of all limitations in claim(s) 1, including (i.e. in combination with the remaining limitations in claim[s] 1) A computer implemented method of improving the accuracy or reliability of an AI system including a LLM (large language model) based system, in which the LLM-based system uses a deep learning model capable of processing natural language and the AI system is capable of generating a sequence of reasoning steps; and in which the AI system includes a non-LLM engine or tool that (i) receives and processes a structured machine-readable representation of one or more of the outputs of the LLM; and (ii) executes a structured verification process that operates using, at least in part, a machine language distinct from natural language.
2025/0182120 (US Patents 12072963 and 11582032 and provisionals 62/906080, 62/954591, and 63/029717 do NOT appear to support the cited passage) teaches “The validated responses are then passed to the Large Language Model (LLM) Module 217, which translates them into semantic triples. This translation process allows the system to represent the response data in a structured, machine-readable format that captures the semantic meaning of the response” (paragraph 262). This portion of this reference does not qualify as prior art.
2022/0308848 teaches “A large corpus of source code programs written in one or more different programming languages is retrieved (block 1002). Each source code program is transformed into an ordered sequence of tuples as described above with respect to FIG. 8 (block 1004). Each ordered sequence of tuples is applied to the trained neural transformer model (block 1006) to output a translated sequence of tokens representing a translation into the second programming language (block 1008). A control token in input into the decoder to identify the second programming language. The application of the ordered sequence of tuples is performed as discussed above with respect to FIG. 9” (paragraph 109). In this reference, the transformer model’s output itself appears to be in the second programming language (i.e. not where there is a programming language representation of the transformer model’s output)
12147758 (LATE filing date) teaches “Upon submitting prompt 409 to the LLM, the prompt engine receives a JSON representation 411 of a pivot table generated by the LLM in response to prompt 409. The prompt engine generates confirmation message 413 for display to the user in the task pane which includes the name of pivot table 415 as extracted from the JSON representation 411. The prompt engine also identifies or configures commands by which the pivot table engine of the application service generates a display of pivot table 415 in the user interface” (col. 11, lines 17-26). This reference does not qualify as prior art.
Double Patenting
For clarity of the record, NO Double Patenting rejections are required between the claims of this application and the claims of the Parent/Sibling applications because the claims of the Parent/Sibling application do not teach or suggest in which the AI system includes a non-LLM engine or tool that (i) receives and processes a structured machine-readable representation of one or more of the outputs of the LLM; and (ii) executes a structured verification process that operates using, at least in part, a machine language distinct from natural language (Claim 1 of US Patent 11,989,527 teaches where an LLM output is represented in machine-readable language and verifying the first output from the LLM, but does not specifically describe the processing system as a non-LLM engine or tool, verifies the LLM output itself [not a representation of an LLM output] and does not specifically describe the verifying operates using a machine language distinct from natural language)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIC YEN whose telephone number is (571)272-4249. The examiner can normally be reached M-F 12:00PM -8:30PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, RICHEMOND DORVIL can be reached at (571)272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
EY 6/8/2026
/ERIC YEN/ Primary Examiner, Art Unit 2658
Prosecution Insights