Appropriateness (1-5)
Does this paper fit in the event? Both empirical and theoretical results are welcome.
5: Certainly.
4: Probably.
3: Unsure.
2: Probably not.
1: Certainly not.
Clarity (1-5)
For the reasonably well-prepared reader, is it clear what was done and why? Is the paper well-written and well-structured?
5 = Very clear.
4 = Understandable by most readers.
3 = Mostly understandable to me with some effort.
2 = Important questions were hard to resolve even with effort.
1 = Much of the paper is confusing.
Originality / Innovativeness (1-5)
How original is the approach? Does this paper break new ground in topic, methodology, or content? How exciting and innovative is the research it describes?
Note that a paper could score high for originality even if the results do not show a convincing benefit.
5 = Surprising: Noteworthy new problem, technique, methodology, or insight.
4 = Creative: Relatively few people in our community would have put these ideas together.
3 = Somewhat conventional: A number of people could have come up with this if they thought about it for a while.
2 = Rather boring: Obvious, or a minor improvement on familiar techniques.
1 = Significant portions have actually been done before or done better.
Soundness / Correctness (1-5)
First, is the technical approach sound and well-chosen? Second, can one trust the claims of the paper — are they supported by proper experiments, proofs, or other argumentation?
5 = The approach is very apt, and the claims are convincingly supported.
4 = Generally solid work, though I have a few suggestions about how to strengthen the technical approach or evaluation.
3 = Fairly reasonable work. The approach is not bad, and at least the main claims are probably correct, but I am not entirely ready to accept them (based on the material in the paper).
2 = Troublesome. There are some ideas worth salvaging here, but the work should really have been done or evaluated differently, or justified better.
1 = Fatally flawed.
Meaningful Comparison (1-5)
Does the author make clear where the problems and methods sit with respect to existing literature? Are the references adequate? Are any experimental results meaningfully compared with the best prior approaches?
5 = Precise and complete comparison with related work. Good job given the space constraints.
4 = Mostly solid bibliography and comparison, but I have some suggestions.
3 = Bibliography and comparison are somewhat helpful, but it could be hard for a reader to determine exactly how this work relates to previous work.
2 = Only partial awareness and understanding of related work, or a flawed empirical comparison.
1 = Little awareness of related work, or lacks necessary empirical comparison.
Thoroughness (1-5)
Does this paper have enough substance, or would it benefit from more ideas or results?
Note that this question mainly concerns the amount of work; its quality is evaluated in other categories.
5 = Contains more ideas or results than most publications in this conference; goes the extra mile.
4 = Represents an appropriate amount of work for a publication in this conference. (most submissions)
3 = Leaves open one or two natural questions that should have been pursued within the paper.
2 = Work in progress. There are enough good ideas, but perhaps not enough results yet.
1 = Seems thin. Not enough ideas here for a full-length paper.
Impact of Ideas or Results (1-5)
How significant is the work described? If the ideas are novel, will they also be useful or inspirational? If the results are sound, are they also important? Does the analysis in the paper bring new insights into the nature of the problem?
5 = Will affect the field by altering other people’s choice of research topics or basic approach.
4 = Some of the ideas or results will substantially help other people’s ongoing research.
3 = Interesting but not too influential. The work will be cited, but mainly for comparison or as a source of minor contributions.
2 = Marginally interesting. May or may not be cited.
1 = Will have no impact on the field.
Recommendation (1-5)
There are many good submissions competing for slots at this event; how important is it to feature this one? Will people learn a lot by reading this paper or seeing it presented?
In deciding on your ultimate recommendation, please think over all your scores above. But remember that no paper is perfect, and remember that we want a conference full of interesting, diverse, and timely work. If a paper has some weaknesses, but you really got a lot out of it, feel free to fight for it. If a paper is solid but you could live without it, let us know that you’re ambivalent. Remember also that the author has a couple of weeks to address reviewer comments before the camera-ready deadline.
Should the paper be accepted or rejected?
5 = Exciting: I’d fight to get it accepted
4 = Worthy: I would like to see it accepted
3 = Borderline: I’m ambivalent about this one
2 = Mediocre: I’d rather not see it in the conference
1 = Poor: I’d fight to have it rejected
Reviewer Confidence (1-5)
5 = Positive that my evaluation is correct. I read the paper very carefully and am very familiar with related work.
4 = Quite sure. I tried to check the important points carefully, and checked for uncited prior work. It’s unlikely, though conceivable, that I missed something that should affect my ratings.
3 = Pretty sure, but there’s a chance I missed something. Although I have a good feel for this area in general, I did not carefully check the paper’s details, e.g., the math, experimental design, or novelty.
2 = Willing to defend evaluation, but it is fairly likely that I missed some details, didn’t understand some central points, or can’t be sure about the novelty of the work.
1 = Not my area, or paper is very hard to understand. My evaluation is just an educated guess.
Detailed Comments
The paper presents EDEN, a large-scale corpus of Italian clinical notes (221M words, 4.2M notes from two Italian hospitals). Of these notes, 5746 notes on patients reported to have suffered from loss of consciousness or dyspnea have been annotated with a Case Report Form (CRF) that is composed of 132 items organized into clinical domains by trained clinicians.
Then, open-weight models have been tested in zero-shot to solve the CRF-filling task, testing three different prompt structures at three different levels of granularity (Item/Group/Full note) finding that the Group prompt was the best performing one, and the Medically pre-trained Gemma the best model for the task.
The paper fills a genuine and well-argued gap: clinical data for Italian is scarce and useful. The reported corpus statistics are somewhat shallow, but provide a sufficient quantitative grounding of how different clinical notes are w.r.t. to other texts in the medical domain. More linguistic analysis of these differences would’ve been appreciated, though.
Regarding the modeling and its evaluation, the Choice of Macro-F1 as the primary metric is grounded and well-motivated, and the baselines provide a useful anchor for the discussion. Also, the discussion on the three granularities of prompts, in terms of efficiency vs quality, is an actionable insight in this domain, and it’s appreciated. However, a fine-tuned classifier as a baseline would have been a nice comparison. While I am sure that for the “Full” scenario, LLMs are more efficient, I am not sure that for the single-item prediction they outperform large-context encoder-based classifiers. Even a comparison on selected items (both high- and low-frequency) would better make the case that LLMs are, overall, better for the CRF-filling task.
On the corpus analysis, reporting the inter-annotator agreement would’ve been appreciated, and especially then looking at what the items are, out of the 132, that make the clinicians disagree the most. This analysis could reveal both useful information about how the notes are written (being ambiguous, for example) or even useful information about how certain medical guidelines are followed and applied differently by different physicians.
Another missed chance is to do error analysis on the model’s output. It would be really informative to look if some of the items are wrong more often, especially in the +Caut setting (Appendix D.), and do some manual analysis of the notes, seeing if there are similarities between the notes that have similar errors. A correlation between the most recurring errors by the model and items with a high disagreement between annotators would show that errors made by the models are reflected in humans too and are learned behavior and biases from medical literature instead of artifacts of a difficult task.
The Appendix D. is really interesting; however, I would like to note that since +Desc doesn’t seem to help, it would strengthen the paper to at least look at some of the generated descriptions to see if they are correct, as it may be the case that that is what is hurting the performance, rather than generating the description being a “distraction”.
Overall, the presented resource is a first step in filling an important gap for the Italian medical domain, and while some more analysis on the corpus and on the model’s output would have been appreciated, EDEN will be an important resource for the development of the Italian Medical NLP field.
Questions for Authors
For the “Full” configuration, do you have any output-validity statistics (e.g. % of notes where the JSON was malformed or missing keys, requiring retries, etc.)? I would expect, especially for the smaller model, that with the requirement of providing a json with 132 different keys, sometimes there could be error or malformations.
Confidential Comments for Committee
You may wish to withhold some comments from the authors, and include them solely for the committee’s internal use. For example, you may want to express a very strong (negative) opinion on the paper, which might offend the authors in some way. Or, perhaps you wish to write something which would expose your identity to the authors. If you wish to share comments of this nature with the committee, this is the place to put them.