PONE-D-24-21873Improving citizen-government interactions with Generative AI: novel human-computer interaction strategies for policy understanding through large language modelsPLOS ONE

Dear Dr. Yun,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Sep 13 2024 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Fredrick Romanus Ishengoma

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at 

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and 

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Partly

Reviewer #2: Yes

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: I Don't Know

Reviewer #2: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: • Present the novelty of the paper in the abstract.

• Improve the quality of figures.

• Add some results in the abstract

• Add the fullform of AI in the title

• In the last paragraph of introduction add the structure of the paper

• Related work section is missing

• The abstract mentions the use of Retrieval-Augmented Generation (RAG) technology combined with Large Language Models (LLMs). Could you provide more detailed information on the specific LLMs used and how RAG technology is implemented in the system? How were these technologies selected and optimized for this application?

• The abstract states that the system was tested with a dataset of policy documents from Chinese and US regional governments. Could you elaborate on the characteristics of this dataset, including the number of documents, the variety of policy topics, and the preprocessing steps involved?

• The abstract indicates that the system generates accurate and comprehensible responses to citizen queries. Can you provide more detailed descriptions of the metrics used to evaluate accuracy and comprehensibility? How were these metrics measured, and what were the baseline comparisons?

• It is mentioned that the system boosts public engagement with government policies. Could you provide specific examples or case studies demonstrating how the system has improved engagement? What metrics were used to assess public engagement?

• The abstract suggests that the proposed system enhances communication of government policies. Could you describe a scenario where this system is implemented in a real-world government setting? What specific steps would be taken to deploy the system, and what are the expected benefits for transparency and citizen engagement?

• How do your recommendations for using RAG technology and LLMs compare to existing methods for policy communication? Are there specific case studies or examples where similar approaches have been successfully implemented?

• The abstract highlights the system's high accuracy in processing and responding to queries. Could you include a comparative analysis with previous studies that have used different technologies or methods for policy communication? How does your proposed model address the limitations identified in these studies?

• Have the results of the proposed system been validated with independent datasets or in different government contexts? If so, please include the validation process and outcomes. If not, what are the plans for future validation?

• The abstract mentions the use of policy documents from Chinese and US regional governments. Could you provide more detailed insights into potential biases introduced by these specific datasets? How do you ensure the generalizability of your findings across different regions and policy areas?

• Can you provide specific scenarios where the proposed approach might face challenges in real-world applications, such as variations in policy language or cultural nuances? How were these challenges identified, and what measures were taken to address them?

• The abstract notes the importance of making government policies accessible and engaging for citizens. Can you describe a scenario where the early implementation of your system helped a government agency effectively communicate a new policy, resulting in improved public understanding and compliance? What factors contributed to the success in this scenario?

• In a scenario where the system is deployed in a large-scale government initiative, what steps would you recommend to ensure continuous performance and accuracy? How would you address potential issues such as data privacy or policy updates?

• The abstract mentions high accuracy in processing and responding to queries. Could you provide more details on the specific performance metrics used to evaluate the system? Were there any specific conditions under which the system's performance varied?

• Can you provide a scenario where the system’s effectiveness might be challenged by variations in policy complexity or citizen query patterns? How would these challenges be mitigated to maintain the system’s performance?

• The abstract discusses the integration of Generative AI and RAG technology for policy communication. Can you provide a detailed comparison of the limitations of traditional policy communication approaches and how your proposed model overcomes them?

• What were the specific limitations encountered during the development and testing of the proposed system? How do these limitations compare to those found in previous studies using conventional methods for government policy communication?

Reviewer #2: The article addresses the critical issue of improving interactions between citizens and government using generative AI and large language models (LLMs). The authors focus on the existing challenges in policy communication, such as accessibility, complexity, and resource constraints, and propose an innovative solution using Retrieval-Augmented Generation (RAG) technology.

The topic of the article is highly relevant in the era of digital transformation. The authors successfully argue the necessity of integrating AI technologies to overcome the existing barriers in government-citizen communication. The innovative approach, which combines RAG and LLM, is promising and shows significant potential for enhancing transparency and citizen engagement.

The article provides a detailed description of a system that integrates LLMs with a retrieval mechanism. The authors explain the architecture of the RAG component and the use of Langchain technology for seamless integration of retrieval and response generation processes. The use case involving policy documents from China and the US demonstrates the system's flexibility and effectiveness across different linguistic and legal contexts.

The experimental results are impressive: the system exhibited high accuracy in processing and responding to citizen queries on various policy matters. Particularly noteworthy are the accuracy rates for numerical questions, highlighting the system's ability to handle quantitative information effectively. However, the authors note a disparity in accuracy between Chinese and American documents, indicating the need for further tuning to accommodate more complex linguistic and legal contexts.

The authors conduct a thorough analysis of the results, highlighting the strengths and weaknesses of the proposed system. The discussion of failed cases provides insights into potential improvements, such as better text extraction and document structuring. The suggestion to improve government policy documentation practices to aid both the AI system and citizen comprehension is particularly interesting.

At the same time, the manuscript suffers from a lack of clear understanding of the article's genre. If it aims to present an experimental validation of the proposed tool, the Introduction clearly fails to fulfill its function. It acts more as an overview of the problem rather than a justification of the relevance and novelty of the research, grounded in previous similar studies on the topic. The authors use studies from other researchers to describe the problem being studied, rather than to justify the boundaries of the knowledge gap being filled and its typology.

If, however, the current manuscript aims to introduce both the tool itself and its validation into scientific discourse simultaneously, then the description of the tool presented appears extremely modest and requires further detailed elaboration. However, this information is not clearly conveyed in the text of the manuscript.

The discussion of the results also requires significant improvement. The authors have only provided their own reflection on the results without integrating them into the existing body of knowledge in the field. In other words, the authors did not engage in an asynchronous dialogue with other researchers on the topic, making it unclear how novel their approach is, what fundamentally sets it apart from existing methods, and other related aspects.

The research topic is quite current, making the absence of recent studies on the topic in the list of references somewhat peculiar. At the very least, these should be incorporated during the revision of the Discussion section.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: Yes: Elena Tikhonova

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

Improving Citizen-Government Interactions with Generative Artificial Intelligence: Novel Human-Computer Interaction strategies for Policy Understanding through Large Language Models

PONE-D-24-21873R1

Dear Dr. Yun,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Jinran Wu, PhD

Academic Editor

PLOS ONE

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #2: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #2: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #2: (No Response)

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #2: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #2: It is crucial to adhere to the genre expression of the manuscript. If the manuscript concerns the testing of a methodology, the article should present the results of an empirical study. If the article is dedicated to introducing a new tool into the international scientific community, it should have a clear structure of a methodological article or, at the very least, a technical note. Currently, the article has a mixed format, including elements of both empirical and methodological research.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #2: Yes: Elena Tikhonova

**********