Thinking Silently for Patent Claim Generation

Lekang Jiang; Wenjun Sun; Stefan Goetz

Thinking Silently for Patent Claim Generation

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

This work investigates whether Chain-of-Thought (CoT) prompting benefits patent claim generation. We demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into structured text generation and CoT applications.

Anthology ID:: 2026.findings-aacl.18
Volume:: Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Month:: November
Year:: 2026
Address:: Hengqin, China
Editors:: Yue Zhang, Ruifeng Xu, Ayu Purwarianti, Tong Rong, Jun Suzuki
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 329–341
Language:
URL:: https://aclanthology.org/2026.findings-aacl.18/
DOI:
Bibkey:
Cite (ACL):: Lekang Jiang, Wenjun Sun, and Stefan Goetz. 2026. Thinking Silently for Patent Claim Generation. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 329–341, Hengqin, China. Association for Computational Linguistics.
Cite (Informal):: Thinking Silently for Patent Claim Generation (Jiang et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-aacl.18.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{jiang-etal-2026-thinking,
    title = "Thinking Silently for Patent Claim Generation",
    author = "Jiang, Lekang  and
      Sun, Wenjun  and
      Goetz, Stefan",
    editor = "Zhang, Yue  and
      Xu, Ruifeng  and
      Purwarianti, Ayu  and
      Rong, Tong  and
      Suzuki, Jun",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
    month = nov,
    year = "2026",
    address = "Hengqin, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-aacl.18/",
    pages = "329--341",
    ISBN = "979-8-89176-444-6",
    abstract = "This work investigates whether Chain-of-Thought (CoT) prompting benefits patent claim generation. We demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into structured text generation and CoT applications."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2026-thinking">
    <titleInfo>
        <title>Thinking Silently for Patent Claim Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lekang</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenjun</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Goetz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-444-6</identifier>
    </relatedItem>
    <abstract>This work investigates whether Chain-of-Thought (CoT) prompting benefits patent claim generation. We demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into structured text generation and CoT applications.</abstract>
    <identifier type="citekey">jiang-etal-2026-thinking</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-aacl.18/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>329</start>
            <end>341</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Thinking Silently for Patent Claim Generation
%A Jiang, Lekang
%A Sun, Wenjun
%A Goetz, Stefan
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F jiang-etal-2026-thinking
%X This work investigates whether Chain-of-Thought (CoT) prompting benefits patent claim generation. We demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into structured text generation and CoT applications.
%U https://aclanthology.org/2026.findings-aacl.18/
%P 329-341

Download as File

Markdown (Informal)

[Thinking Silently for Patent Claim Generation](https://aclanthology.org/2026.findings-aacl.18/) (Jiang et al., Findings 2026)

Thinking Silently for Patent Claim Generation (Jiang et al., Findings 2026)

ACL

Lekang Jiang, Wenjun Sun, and Stefan Goetz. 2026. Thinking Silently for Patent Claim Generation. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 329–341, Hengqin, China. Association for Computational Linguistics.