- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper investigates whether models with nearly identical task performance exhibit consistent responses to the same input intervention. The authors construct a synthetic assignment task in which two candidate rules, RECENCY and RARITY, always produce identical answers on the training distribution. They then introduce an answer-preserving multiplicity inversion that changes the relative frequencies of competing values while keeping the correct answer unchanged. Intervention sensitivity is measured through changes in the log-odds ratio between the old and new values. The main finding is that similar task performance does not guarantee reproducible intervention responses. Importantly, the authors also show that such differences should not be directly interpreted as evidence of different answer-selection policies or internal mechanisms.
Critical strengths
- A controlled experimental setting for studying intervention reproducibility.
- Extensive empirical evidence and careful interpretation of intervention measurements. It remains unclear to what extent the observed cross-run variation generalizes to realistic language understanding or reasoning tasks, where competing cues are rarely perfectly equivalent.
Critical weaknesses
- Insufficient motivation and unclear positioning of the central research contribution. The paper does not clearly establish the broader research problem or the gap it aims to address.
- Limited generalizability and insufficient explanation of the observed intervention differences.
- The paper suffers from poor organization and unclear exposition, making it difficult to follow the central research question, understand the motivation, and distinguish the main contributions from the extensive experimental details.
Questions for authors
Please refer to the weaknesses above.