- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes STOU, a benchmark tailored for safety issues in egocentric multi-modal scenarios. This benchmark contains 2,902 samples, each sample is a short first-person video paired with a harmful query in text and speech. The queries are categorized by who will be harmed (Self, The Others, Others and Unspecified), and also by six harm types. Beside the refusal rate, the authors also propose to evaluate the safety understanding of model where they require the model to recognize the possible intend of users and consequences it might cuase. Evaluating on 10 open-source and close-source models, the authors find that the refusal behavior differ across harm targets and models often understand the harm but still decide to help the user.
Critical strengths
- This paper targets at a practical scenario where AI assistants are helping users with egocentric devices. Existing safety benchmarks mostly focus on exocentric view or text/image input, and they do not consider who will be harmed. So I think categorize the harmful queries by harm target is a reasonable and useful perspective for this setting.
- The authors design detailed probing questions to decouple the model’s understanding of the unsafe action from its refusal behavior. They not only check if the model refuse or not, but also ask the model about the user’s intended action, the affected party and consequence of the harm.
Critical weaknesses
- The metric design is not well explained. The paper does not explain why affected party gets 1 point while mechanism and consequence get 2 points and why select τ=3. With this setting, a model can get the affected party wrong and still count as “understood” which is strange because it seems the most important focus of this paper is the Harm Target.
- The ground truth generation relies heavily on LLM. The gold answers are generated by GPT-4.1 and the judge is also GPT-4.1. More importantly, there seems to be no human check on the gold answers. Therefore, it is hard to say whether they are reliable standard.
Questions for authors
- Can the authors explain the reason behind the 0-3 score range for refusal evaluation and 1/2/2 score weights for understanding probe? And what will the results look like if you require the affected party to be correct for “understood”?
- Are the gold answers generated by GPT-4.1 checked by human? If so, how many of them are wrong or modified?
- The understanding probe already tells the model the query is data and directly ask whether it is harmful, which might be a strong hint. How do you make sure the alignment gap is not just caused by this prompt difference?
- Do the 393 human-written queries and the LLM-generated queries show different results? It would be good to report them separately.
- There are some writing issues that make the paper confusing. Could the authors fix them?
- Table 10’s caption has a broken reference.
- The caption for figure 2 and 3 are repeated. The order of the index is also wrong.
- Table 1 and Table 9 have exactly the same content.