- Rating
- 4
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper investigates how language models represent relational information during multi-hop reasoning in J space. Through controlled graph reasoning tasks and causal interventions, the authors find that entities remain accessible across layers but relations are more localized in middle layers. The findings suggest that the workspace mostly carries entities without preserving the relations.
Critical strengths
- Well motivated research question and careful experimental design. It studies and interesting question of how language models represent structured information during reasoning. The design of minimal edge-pair and the specific causal interventions makes the results convincing.
- Comprehensive analysis and extensive experiments. Lens-coordinate interventions, subspace transfer, and probing provide a coherent picture. The experiments also span 8 models multiple layers. I also appreciate the analysis connecting workspace capacity to reasoning failures, which gives the representational findings a meaningful behavioral interpretation.
Critical weaknesses
The paper argues that the workspace never contains a bound graph because entity and relation interventions do not have overlapping causal effects. But this remains unknown if we move beyond towards more distributed or nonlinear representations of relational binding.
Questions for authors
In Section 4.7, the authors find that relational information shifts from J space to directions outside J space in Qwen models but not Gemma. Do the authors have any hypotheses about what explains this difference?