- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper investigates how quantization and tool-use fine-tuning jointly affect the safety of small language model agents. Using a 2×2 experimental design across six models, it finds that their interaction varies substantially across models and that reduced harmful tool invocation can partly reflect degraded tool-use capability rather than improved safety. The results and analysis show the model still recognize requests as harmful, but quantification and tool fine-tuning have changed ites tendencu to take action.
Critical strengths
Interesting empirical phenomenon. The paper investigates how quantization and tool-use fine-tuning jointly affect small-model agent.
Critical weaknesses
-
Presentation and consistency issues. The paper contains formatting problems and unclear wording.
-
Insufficient analysis of the fine-tuning data. The paper does not clearly describe whether the training data are screened for harmful requests or include safety-oriented refusal examples. Tool-use fine-tuning without explicit safety supervision may increase general compliance, including compliance with harmful requests. it is a very natural process for the model to answer these questions after training. Why do articles need to analyze fine-tuning and quantification together.
Questions for authors
-
Evaluation on additional datasets. Could the authors validate the central findings on additional benchmarks where harmful tool use can be distinguished from ordinary tool invocation? Most supporting evidence comes from AgentHarm, while the other benchmarks provide limited or inconsistent support.
-
Generalization to larger models. Do the findings persist on larger models, such as 7B–8B models or above? Since the current models range from 0.5B to 3.8B parameters, some observed effects may reflect the limited capabilities and greater fragility of very small models under quantization.