- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper introduced a TriAxis-CF dataset which includes 300 factual/counterfactual image pairs to discover causal represented spatial features. They compared fully shared, relation-selective, and shared–private control in Qwen 3 to find that adaptive partial sharing is the best for error correction and correct answer preservation. The proposed SP-LoReFT demonstrated improved accuracy and decreased breaks.
Critical strengths
The paper is generally well motivated. How spatial reasoning is represented and controlled in VLMs, especially with specific relations, provides useful insights for improving spatial reasoning capabilities. The paper presents a systematic framework including controlled spatial counterfactuals, activation-based causal analysis, and low-rank representation intervention.
Critical weaknesses
- Dataset size of 300 is small. The small dataset raises concerns about the representativeness of the mechanistic findings. The diversity of spatial configurations and scenes does not capture real-world spatial reasoning. Given the small evaluation set, the modest improvement results on SP-LoReFT (88.33% to 90.56%) further limit the effectiveness of the conclusion.
- The evaluation uses three spatial relationships (far/near, left/right, tall/short) under controlled visual settings, without sufficiently establishing whether the learned interventions transfer to more complex spatial reasoning tasks or real-world images.
Questions for authors
- The evaluated Qwen3-VL-8B-Instruct, InternVL3.5-8B, Idefics3-8B-Llama3, and DeepSeekVL-7B-Chat differ in their visual encoders, multimodal fusion mechanisms, and internal architectures. Since the paper investigates the distribution of causal sensitivity across model layers and token positions, could the authors clarify how these architectural differences affect the observed patterns? How are the intervention sites defined and aligned across models with different visual-token representations and fusion mechanisms? To what extent can the findings be generalized to alternative VLM architectures, such as cross-attention-based or late-fusion models?
- The paper is only 6 and a half pages, using the full 9 pages to include more comprehensive analysis and results will strengthen the paper.
- Minor: the AI USE STATEMENT is supposed to be put before the references.