- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper audits how MIB evaluates discovered circuits. It decomposes CPR and CMD into overshoot and undershoot, examines published results, and re-evaluates public submissions. Its central experiment shows that removing two known suppressive connections from an IOI circuit increases CPR while making the circuit less complete. Additional experiments examine the effects of counterfactual choice and distinguish suppression removal from more extreme overshoot.
Critical strengths
The paper connects a concrete evaluation problem to a direct intervention: removing known components of the IOI mechanism improves the benchmark score. The deletion controls and restoration experiments make this more convincing than an observation that faithfulness sometimes exceeds one.
The analysis also leads to useful recommendations about evaluating the same circuit family and distinguishing behavioral agreement from task performance. The authors acknowledge prior observations and report limitations and unsuccessful predictions.
Critical weaknesses
-
The presentation could be clearer. The abstract includes many results and numerical details before the scoring setup is established. A simpler introduction to the selection rules and metrics would help. Figure 3b also feels cramped: the labels and legend take up substantial space relative to the plotting area, and several markers overlap. The layout should be revised, and the caption should explain the horizontal bars.
-
The experimental coverage limits the broader conclusions. The detailed intervention study centers on GPT-2 Small and IOI. The Qwen experiments provide useful extensions but use only 32 IOI and 50 MCQA examples, and only EAP is rescored under both counterfactuals. The published-table audit establishes that overshoot is widespread, but it does not establish that the same mechanism explains it across those settings.
-
The novelty is mainly in the empirical audit. As Section 1 acknowledges, prior work had already identified over-optimization of task metrics and the omission of negatively contributing components. The score decomposition is useful but mathematically straightforward. The contribution lies in quantifying the consequences for MIB and demonstrating them through interventions. The abstract and discussion could emphasize this more clearly and expand on what the findings imply for MIB’s two explicitly different evaluation goals.
Questions for authors
-
Could the scoring/evaluation counterfactual comparison be repeated for another method? This would help determine whether the result that the evaluation counterfactual sets the side of one extends beyond EAP.
-
How stable are the Qwen IOI and MCQA intervention effects with more evaluation examples? Additional examples and uncertainty estimates would strengthen the evidence beyond the main GPT-2 IOI setting.
-
Section 9 notes that the recommended per-example distance does not reliably distinguish four of the submissions at the current sample size. Could you discuss whether larger samples are likely to resolve this, or whether these methods are simply behaviorally similar under magnitude selection? This matters for using the proposed distance as a headline ranking metric.
-
Could you expand the discussion of CPR’s remaining role? Since MIB explicitly assigns it a task-performance objective, would retaining CPR under that interpretation, alongside a separate behavioral-faithfulness ranking, address the main concern?
-
Figure presentation: In Figure 3b, the text and labels take up too much space relative to the plotting area, making the panel feel cramped. Could you adjust the font sizes, enlarge the plotting area, and tidy up the layout to make the comparisons easier to follow? Could you adjust the layout and font sizes, and check the other figures for similar readability issues?