- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper decomposes changes in prediction loss with document position into composition and dilution effects. Composition captures changes in the proportions of tokens with different prior occurrence counts, while dilution captures changes in the average loss within each count group. For Pythia on FineWeb, the authors observe that average loss decreases while count-conditional losses increase, which they identify as a Simpson’s paradox. They examine these measurements across model sizes, text domains and training checkpoints.
Critical strengths
None.
Critical weaknesses
The paper does not sufficiently clarify what scientific conclusion follows from the loss decomposition. The observed reversal is compatible with a simple model performing successful inference from context. Consider the add-one predictor where counts occurrences of token among the first tokens and is the vocabulary size. Its loss at fixed count is which increases with position. This predictor is also the Bayesian posterior predictive for a document-specific categorical distribution drawn from a uniform Dirichlet prior. In that setting, expected aggregate loss decreases as the predictor infers the document’s distribution, despite increasing loss at every fixed count. Thus, the reversal alone does not establish that the aggregate improvement gives a misleading impression of context use.
The authors acknowledge that the observed reversal does not imply a failure to use context. However, this leaves the scientific and practical implications of the decomposition underdeveloped. In particular, the recommendation to report token-group losses needs a concrete demonstration of what these measurements allow us to infer.
In addition, in my opinion, the issues raised in the following "questions for authors" section are not mere presentation issues, but rather indicators that the current submission doesn't meet the scientific standard required for publication, independently of the strength of the contribution.
Questions for authors
-
Can the authors demonstrate a concrete use of the token-group losses to assess context use or distinguish models? In particular, what conclusion would be missed or incorrectly drawn from the aggregate loss, and how would the group losses resolve it despite the changing targets within each group?
-
How should the controlled synthetic experiments in section 4.3 change our interpretation of the position-based score? The Bayes-optimal score itself depends on the synthetic distributions, indicating that the available benefit of context depends heavily on the data. How do these experiments distinguish a limitation of the score from a genuine difference in the predictive information supplied by context?
-
Terminology should be consistent between the main text and figures, particularly “first occurrences” versus “novel” and “within-group change” versus “dilution.” Why use different terminology for the main text and figures/figure captions?
-
The schematic graphics in Figures 2 and 3 are more elaborate than necessary; simpler illustrations or a direct report of the relevant measurements, possibly on a graph, would make the argument easier to follow.
-
Why do the authors report rates per e-fold of position instead of just position?