DETAILED ACTION
This action is responsive to the amendments filed 8/13/2026.
Claims 1-11 and 13-21 are pending. Claims 1-3, 8, 9, 11, 13, 18 and 19 are currently amended; Claim 12 is canceled and Claim 21 is new.
All prior rejections under 35 U.S.C. § § 102-103 are withdrawn as necessitated by amendment.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 2, 4, 5, 11, 14 and 18-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Hunter, et al., U.S. PGPUB No. 2025/0298816 (“Hunter”).
With regard to Claim 1, Hunter teaches a method, comprising:
receiving, by a processing device, a prompt and one or more documents ([0028] describes that a user submits a query related to a document or set of multiple documents and provides the document along with the query);
generating, by the processing device and using a generative text model, an answer to the prompt supported by the one or more documents ([0029]-[0032] describe that the document is processed to generate an outline and metadata, which are then submitted to a large language model along with a prompt to generate a response to the query based on the document outline and metadata);
decomposing, by the processing device and using a text decomposition model, the answer into a plurality of statements; and attributing, by the processing device and using a natural language inference model, a statement of the plurality of statements to one or more sentences of the one or more documents ([0033] describes that the document application can correlate selected sentences from the natural language response to respective sentences from the submitted document and generate citation information indicating the correlated sentences. [0037] describes that a LLM and one or more embedding models can be used to generate the source matching information); and
generating, by the processing device, one or more annotated documents including at least one visual indication associating the statement with the one or more sentences ([0034] describes that the application can display the received response and highlight the sentences in the document correlated to the selected sentences of the response, as indicated in the received citation information).
Claim 11 recites a system comprising a processing device and a memory storing instructions that are executable by the processing device (Fig. 13) to perform a method substantially the same as the method of Claim 1, and is similarly rejected. Claim 18 recites a non-transitory computer readable medium storing executable instructions, which executed by a processing device, cause the processing device to perform operations ([0086]) comprising the method of Claim 1, and is likewise rejected.
With regard to Claim 2, Hunter teaches that the prompt requests generation of the answer relying solely on content of the one or more documents. [0026] describes that users submit queries to the system to obtain answers to questions regarding a document.
Claim 19 recites a non-transitory computer readable medium storing executable instructions, which executed by a processing device, cause the processing device to perform operations ([0086]) comprising the method of Claim 2, and is similarly rejected.
With regard to Claim 4, Hunter teaches that the attributing includes attributing the statement to multiple sentences in the one or more documents. [0058] describes that the system can determine and provide a predetermined number of source sentences as supporting a given answer portion.
Claim 20 recites a non-transitory computer readable medium storing executable instructions, which executed by a processing device, cause the processing device to perform operations ([0086]) comprising the method of Claim 4, and is similarly rejected.
With regard to Claim 5, Hunter teaches that the attributing the statement to the one or more sentences includes: generating, using the natural language inference model, attribution scores measuring degrees to which the statement is inferable by respective sentences in the one or more documents; and attributing the statement to a sentence in the one or more documents based on the attribution scores, the sentence having a first attribution score. [0056]-[0058] describe that document sentences are ranked according to highest embedding comparison match, and then selected by the citation generator on the basis of being the highest matching sentences.
Claim 14 recites a system comprising a processing device and a memory storing instructions that are executable by the processing device (Fig. 13) to perform a method substantially the same as the method of Claim 5, and is similarly rejected.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 3, 6, 10, 13, 16, 17 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Hunter, in view of Snider, et al., U.S. PGPUB No. 2015/0006199 (“Snider”).
With regard to Claim 3, Hunter does not teach that the decomposing includes decomposing at least one sentence of the answer into multiple statements, the plurality of statements representing different facts, opinions, or propositions expressed in the answer. Snider teaches at [0167] and Fig. 7A that multiple facts have been extracted from one sentence of the input text.
It would have been obvious to one of ordinary skill in the art at the time this application was filed to modify Hunter to enable the extraction of multiple facts from a single sentence, as described in Snider. One of skill in the art would have sought the modification, to improve system functioning by enabling more precise decomposition, ensuring that multiple assertions in compound sentences are properly attributed with citations in the final output.
Claim 13 recites a system comprising a processing device and a memory storing instructions that are executable by the processing device (Fig. 13) to perform a method substantially the same as the method of Claim 3, and is similarly rejected.
With regard to Claim 6, Hunter, in view of Snider does teaches that the attributing the statement to the one or more sentences includes: generating, using the natural language inference model, a second attribution score measuring a degree to which the statement is inferable by a combination of the sentence and an additional sentence of the one or more documents; and attributing the statement to the sentence and the additional sentence based on the second attribution score exceeding the first attribution score.
Snider at [0146] describes that the model incorporates cascading models. [0147] describes extracting additional facts related to an initially identified fact as additional attributes of the fact, where the text analyzed for additional attributes can be of any suitable length. The extracted fact can then be linked to an entire sentence or even a paragraph as a result of the context determined for the fact. As Hunter teaches at [0056]-[0058] that matching to the original text is carried out by ranking computed embedding matches, linking can be carried out to multiple sentences based on a higher score.
It would have been obvious to one of ordinary skill in the art at the time this application was filed to modify Hunter to enable the linking of multiple sentences in support of a portion of an answer. One of skill in the art would have sought the modification, to improve user experience by ensuring that multi-sentence support for a portion of an answer can be provided when needed to ensure the user is provided with the optimal support for answer portions.
With regard to Claim 10, Hunter does not teach receiving user feedback interacting with the one or more annotated documents, the user feedback indicating updated attributions attributing the statement to at least one different or additional sentence in the one or more documents, wherein the natural language inference model is trained based on a degree of difference between attributions as generated by the natural language inference model and the updated attributions.
Snider teaches at [0189]-[0191] that a user can delete facts, as well as add facts by adding an extracted fact and associating it with a selected portion of the text. Therefore, a user may change a text portion to which a fact was associated by deleting a fact and adding the fact associated with a different portion of the text. [0195] describes that a user correction can be used to re-train one or more of the statistical models used in fact extraction, including by weighting the label differently from the original training data that led to the incorrect label, such as by weighting the user correction more heavily.
It would have been obvious to one of ordinary skill in the art at the time this application was filed to modify Hunter to enable the feedback and training that is described in Snider. One of skill in the art would have sought the modification, to improve system functioning by providing additional training of language models using feedback, thereby improving the functioning of models in making future determinations about the similarity between answer portions and portions of input documents.
Claim 16 recites a system comprising a processing device and a memory storing instructions that are executable by the processing device (Fig. 13) to perform a method substantially the same as the method of Claim 10, and is similarly rejected.
With regard to Claim 17, Hunter does not teach that the natural language inference model is trained based on a degree of difference between original attributions of the statement to the one or more corresponding portions of the content as generated using the natural language inference model and updated attributions of the statement to the at least one different or additional portion of the content as indicated by the user feedback.
Snider at [0195] describes that a user correction can be used to re-train one or more of the statistical models used in fact extraction, including by weighting the label differently from the original training data that led to the incorrect label, such as by weighting the user correction more heavily.
It would have been obvious to one of ordinary skill in the art at the time this application was filed to modify Hunter to enable the feedback and training that is described in Snider. One of skill in the art would have sought the modification, to improve system functioning by providing additional training of language models using feedback, thereby improving the functioning of models in making future determinations about the similarity between answer portions and portions of input documents.
With regard to Claim 21, Hunter, in view of Snider teaches wherein the attributing includes attributing the statement to multiple sentences based on a first attribution score generated using the natural language inference model for a combination of the multiple sentences exceeding a second attribution score generated using the natural language inference model for an individual sentence of the multiple sentences.
Snider at [0146] describes that the model incorporates cascading models. [0147] describes extracting additional facts related to an initially identified fact as additional attributes of the fact, where the text analyzed for additional attributes can be of any suitable length. The extracted fact can then be linked to an entire sentence or even a paragraph of the input text as a result of the context determined for the fact. As Hunter teaches at [0056]-[0058] that matching to the original text is carried out by ranking computed embedding matches, linking can be carried out to multiple sentences based on a higher score.
It would have been obvious to one of ordinary skill in the art at the time this application was filed to modify Hunter to enable the linking of multiple sentences in support of a portion of an answer. One of skill in the art would have sought the modification, to improve user experience by ensuring that multi-sentence support for a portion of an answer can be provided when needed to ensure the user is provided with the optimal support for answer portions.
Allowable Subject Matter
Claims 7-9 and 15 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Response to Arguments
Applicant’s arguments with respect to Claims 1 and 5 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEITH D BLOOMQUIST whose telephone number is (571)270-7718. The examiner can normally be reached M-F, 8:30-5 PM.
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, Kieu Vu can be reached at 571-272-4057. 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.
/KEITH D BLOOMQUIST/Primary Examiner, Art Unit 2171
9/10/2026
Prosecution Insights