Reviewer has chosen to be Anonymous

Overall Impression: Good

Content:
Technical Quality of the paper: Good
Originality of the paper: Yes, but limited
Adequacy of the bibliography: Yes, but see detailed comments

Presentation:
Adequacy of the abstract: Yes
Introduction: background and motivation: Good
Organization of the paper: Satisfactory
Level of English: Satisfactory
Overall presentation: Good

Detailed Comments:

In this paper, the authors provide an overview of the existing literature on neuro-symbolic methods for trustworthiness, where this notion is seen as composed of five dimensions: interpretability, safety, robustness, fairness, and privacy.

A strength of the paper is its clarity, especially with regard to the methodological choices made for selecting the articles to consider in the survey.

Nonetheless, the work in its present form has some crucial weaknesses to be addressed:

\begin{itemize}
\item[--] First and foremost, the article lacks of a proper discussion of the papers surveyed. This is usually done by providing a synthetic, though effective, description of each paper surveyed. Alternatively, the survey can highlight common perspectives, strategies, results, etc. among the papers. This is done in part in Sections 4.1 and 4.2. However, we believe that the level of detail of these sections is not sufficiently fine-grained to fully deliver the potential of a survey paper, where the reader should gain specific knowledge about the surveyed articles.
\item[--] There seems to be an inconsistency in the information about the timeframe considered for the survey. Although it is initially declared that the work constitutes a systematic review of the recent literature from 2021 to 2022 (page 2 line 8), the authors then say that they ``focused on papers published in top academic venues from 2021 to 2023, including those available up to May 2023" (page 5 line 8). Moreover, Figure 1(a) is in line with the former statement and contains no information on 2023 papers.
\item[--] Finally, the general impression is that the actual scope of this survey is interpretability alone. As the authors themselves point out, ``interpretability is the most extensively addressed aspect of trustworthiness" (page 3, line 24). The other four aspects -- robustness, fairness, privacy, and safety -- have a marginal discussion in the work. This is due to two different reasons. As far as robustness is concerned, the authors intentionally left out studies mainly centered on robustness, arguing that the concept is overly intertwined with that of accuracy. Regarding fairness, privacy, and safety instead, we have to wait until Section 4.4 to learn that there is a scarcity of neuro-symbolic applications for these topics (only one paper is mentioned, in relation to fairness).
\end{itemize}

Questions:
\begin{itemize}
\item[--] What justifies the methodological choice of focusing on proceedings papers only? Neuro-symbolic AI is a hybrid research topic, in the middle ground between computer science and logic, a field where journal papers have high relevance (e.g. the journal Neurosymbolic AI to mention one).
\item[--] Why the following paper was excluded by the survey? Wagner, B. \& d'Avila Garcez, A. S. (2021). Neural-symbolic integration for fairness in AI. In: CEUR Workshop Proceedings. AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021), 22-24 Mar 2021, California, USA.
\end{itemize}

Finally, we suggest some minors improvements to the text:
\begin{itemize}
\item[--] Legend of Figure 1(b) contains the typo ``where taken";
\item[--] Figure 3: we suggest changing the abbreviation ``AMB" for ``ambiguous" with a more self-explanatory expression - ``ambiguous" or ``unclear" should be fine.
\end{itemize}

=== final meta-level thoughts ==

I think it would be good to have some sort of comparison to existing works that discuss XAI and trustworthiness from a non NeSy AI context, and particularly to human modelling, and discussions on well-established surveys and experimental evaluations (e.g., stakeholder discussion cf Adrian Weller, Trustworthiness and XAI taxonomy by Nathalie Rodriguez and colleagues). There is an attempt to classify existing works which is appreciated but further work is needed in terms of updating the reader on non NesyAI solutions. Therefore, how well are NeSy AI solutions addressing these concerns? What's hard to do (see work on XAI planning and explaining in dynamic domains).

Reviewer has chosen not to be Anonymous

Overall Impression: Average

Content:
Technical Quality of the paper: Average
Originality of the paper: Yes, but limited
Adequacy of the bibliography: Yes

Presentation:
Adequacy of the abstract: Yes
Introduction: background and motivation: Good
Organization of the paper: Needs improvement
Level of English: Satisfactory
Overall presentation: Good

Detailed Comments:

This paper focuses on applying Neuro-Symbolic (NeSy) methods to interpret deep learning systems. It proposes a novel, comprehensive, and multi-perspective framework that systematically categorizes and analyzes recent literature in this field.

Reasons to accept:
1. The paper categorizes existing articles reasonably, integrating NeSy methods to increase the trustworthiness of deep learning systems.
2. The paper defines different types of NeSy methods mainly from two perspectives, Symbolic Data Structures and types of interpretability.
3. The proposed categories proposed are clear and move toward addressing the problem of unclear categorization in NeSy field.
4. Although the paper lacks quantitative analysis, it does keep the discussion from going deeper and more reliable. It doesn't really influence the framework they proposed.

Reasons to reject:
1. There is insufficient forward-looking discussion. Although the paper mentions future research directions, it may lack sufficient innovative discussion or foresight. In particular, the paper points out the lack of NeSy applications in privacy and fairness, but provides no further insight into it.
2. The paper lacks a quantitative analysis, which keeps the discussion superficial. There also seems to be a lack of listing current metrics or standards to measure how the NeSy model enhances model interpretability.
3. The writing style is wordy and there are many internal repetitions. For example, in Section 3, the paper mentions they “selected the papers directly contributing to trustworthiness” three times.
4. The paper suffers from unclear citations. In Section 1.2, line 43, the paper mentioned “some systems”, but no clear reference can be found to prove the argument. Specific references should be provided.
5. Time conflict. In Section 1, the paper notes that the studied article is from 2021-2022, but in Section 3 they are mentioned from 2021-2023. The conflict may confuse the audience.
6. In Section 3, the paper claims they have surveyed the papers from AACM FAccT, but Fig.1(b) shows there is 0 paper coming from AACM FAccT. The paper may point out less content related to NeSy for Trustworthy in AACM FAccT, but fails to demonstrate it explicitly.
7. Consider adding an overview paragraph to make it easier for purposeful readers to quickly locate the section they need.
8. The paper could describe the content of Table 1 more clearly in the caption.