- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes a token-axis predictive decomposition of language model hidden states into a predictive component, estimated from preceding hidden states, and an innovation component defined as the prediction residual. Using Pythia-410M, the authors analyze their temporal structure, linguistic attribute decodability, and effects on the model's output distribution. The results show differences in temporal persistence and linguistic decodability between the two components, as well as asymmetric output sensitivity to scaling the innovation.
Critical strengths
- Well-defined token-axis analysis framework. The paper introduces a principled decomposition that separates information predictable from preceding hidden states from the remaining prediction residual. Unlike retrospective contextual decomposition, the predictive component is estimated without observing the current token.
- Interesting empirical observations. The analysis reveals consistent differences in linguistic decodability between the two components. In particular, the relative decodability of linguistic attributes shifts toward the predictive component in deeper layers, providing an interesting perspective on representation structure.
Critical weaknesses
-
The interpretation of innovation is insufficiently validated. The true conditional expectation is approximated using finite-capacity predictors, so the residual may contain contextual information that the predictor fails to capture. Near-zero autocorrelation alone does not establish that the learned residual closely approximates the theoretical innovation. This limits the strength of the paper's interpretation of the two components.
-
The significance of the empirical findings remains limited. Several observations, such as low innovation autocorrelation and the separation between context-dependent and token-local attributes, are broadly consistent with the proposed decomposition. Moreover, similar intervention asymmetry appears with simple baselines, including global-mean replacement and copying. While the framework is reasonable and the experiments are informative, it remains unclear what substantial new insights it provides beyond existing approaches such as TFA and PHi.
Questions for authors
- Does the residual retain information predictable from past hidden states? Are the findings robust to improved predictors?
- What insights does this decomposition uniquely provide beyond TFA and PHi, particularly regarding intervention asymmetry?