- Rating
- 2(+1)
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The authors of the paper examine the problem of connection between attention patterns and heads divergence. Since a head’s output depends on both its attention row and its value vectors, the authors prove that attention rows alone leave the output distance undetermined, while the Gram matrix of the projected values fixes it. In order to do so, they consider an attention row as a point of the probability simplex over key positions and the head output as , where holds the projected value vectors. The first position is treated as a sink, so each row splits into a sink mass and a content distribution , . They show that over value matrices with bounded rows, the output distance can take any value in , whereas it equals exactly the Gram distance . Using this identity they decompose Jensen-Shannon divergance by two parts: sink term and non-sink term. Based on the following idea they propose:
-
Theoretical examination of heads. They state that it should be compared via their projected value vectors (e.g., the Gram distance or the full output distance), since similar attention patterns are not evidence of similar function.
-
Pattern similarity vs. output similarity. On within-layer head pairs of GPT-2, Pythia-160M and Llama-3.2-1B (WikiText-103), the authors test how well attention-pattern scores predict the distance between head outputs.
-
Practical examination (like head-prunning). When 10-30% of the heads in each layer are removed or replaced, selection by value-aware distances increases perplexity less than selection by attention patterns in most settings.
Critical strengths
- The authors provide the accurate formulation to the problem. They precisely explain why it is necessary to consider the projected values and take in the account sink part. The sink-content decomposition explains precisely when keeping or masking the sink token changes conclusions.
Critical weaknesses
-
Limited idea. The main proposition to consider differentiate the sink part out of the other tokens is well-examined (even in the context of Gramm matrices) [like to noted in Kobayashi et al. 2020 and Xiangming Gu et al. 2024]. Much of your theory is a formalization of the linearity of the head output. Moreover, the key empirical finding is that output distance is driven almost entirely by head norms, since outputs within a layer are nearly orthogonal. As a result, the proposed “functional distance” mostly measures scale rather than function.
-
No practical gain for the real models. Experiments use only small models (up to 1B parameters), short windows of 192 tokens, and perplexity on WikiText-103, without the BOS token that models like Llama normally use.
Questions for authors
-
What can you say about the comparison of your paper to the research of Kobayashi et al. and Xiangming Gu et al.?
-
What your theoretical results (Th.1 and Th.3 f.e.) could propose to the researchers from the practical point of view?
Respond to reviewer W5hb
Thank you for the review. Each limit you name now has an experiment. On three larger models, and on Llama-3.2-1B with BOS, replacing heads by partners chosen with S costs less than the best removal rule at every budget. The theory gives five concrete instructions. Changes are blue in the revised PDF, and the new analyses were chosen after the reviews (Appendix L).
Q1, W1. Kobayashi et al. and Gu et al. Kobayashi et al. measure the norm of each weighted value inside one head. Gu et al. describe the sink as a key bias whose value has a small norm. Neither compares two heads. Norms are the diagonal of the Gram matrix, and the distance between two heads needs the inner products across heads. In case A of new Table 1, two heads have equal patterns and equal norms at every token, and their outputs are orthogonal. The closest measurements are the average disagreement of Li et al. (2018) and the swap measure of Haklay et al. (2026). To our knowledge, no earlier work tests a pattern score against the output distance of the same two heads. On the sink our data agree with both papers, and our test does not show the mechanism of Corollary 2 (Table 30).
W1. Linearity and scale. We agree that Theorem 1(a,b) follows from linearity. The contribution is the measurement on trained heads. You are right that head norms set most of D (0.94 to 0.98). We therefore rescaled every output to unit norm. Pattern scores correlate with this scale-free distance at −0.17 to −0.03 and recover 4 to 15 percent of its neighbours (chance 3 to 9). The Gram distance of unit-norm outputs reaches 0.50 to 0.67 (Table 19). Scale is also part of what a head does, and Sandoval-Segura et al. (2025) find that output norms identify inactive heads.
W2. Scope. We add six models of up to 7.6B parameters (Qwen2.5-7B), windows of 1,024 tokens, a second corpus (C4) and BOS at the start of every window (Tables 22 to 24). Gu et al. also compute their sink metric on 64-token sequences without BOS. In every setting, averaged pattern scores recover 0.9 to 12 percent of output neighbours (chance 3 to 9), and head norms recover more than half. The condition S<Nh holds for 47 to 64 percent of the pairs that share values and for at most 1.6 percent of the others.
W2. Practical gain. The gain is a test that needs no training. From one set of forward passes, S<Nh tells which head can replace which, and where replacement will fail.
(1) In grouped-query models, the design of Llama 3 and Qwen2.5, S finds heads that are cheaper to replace than to remove. Replacing 10 percent of the heads of every layer raises perplexity by 4, 2 and 2 percent on Llama-3.2-3B, Qwen2.5-1.5B and Qwen2.5-7B, against 17, 27 and 10 for the best removal rule (Table 23). On Llama-3.2-1B the costs are 6 against 28, and 3 against 5 with BOS. In these five settings substitution costs less at all three budgets.
(2) The test predicts the outcome pair by pair. Substitution costs less than removal for 74 to 85 percent of the pairs that pass and for 8 to 20 percent of the others. Inside key-value groups the shares are 74 to 88 and 45 to 54 percent (Table 25).
(3) The test also says where not to substitute. Without shared values, fewer than 2 percent of pairs pass. On GPT-2 and Pythia the best removal rule is then cheaper in the main protocol and in 16 of 18 cells of the other settings.
On Llama-3.2-1B the gain varies with the setting. On C4, substitution is cheaper at 20 and 30 percent (51 against 61, and 191 against 387) and removal at 10 percent (21 against 37). With 1,024-token windows the two are level at 30 percent (159 against 162) and removal is cheaper below. Perplexity remains our downstream metric, and we present the edits as a diagnostic.
Q2. What the theory proposes in practice. Theorem 1 gives two instructions.
(1) Do not choose heads to merge, prune or match across models by their attention maps. For any pattern score there are values that reverse its ordering (part a), and on nine models these scores recover output neighbours near chance.
(2) Compute the quantities of part (b), the head norms and the Gram blocks of the values. The same forward passes give them. Norms alone find the head with the closest output for 58 to 86 percent of heads (Table 22).
Theorem 3, with Theorem 2, gives two more.
(3) State whether the sink or BOS is kept or masked, and report the sink masses and the content distance as two numbers. The choice reverses 21 and 26 percent of JS verdicts on GPT-2 and Llama, and Theorem 2 gives the term that masking removes.
(4) A better pattern metric will not close the gap. Under the axioms of Theorem 3, the only scores that separate every key are multiples of the Aitchison distance, which correlates with D at 0.06 at most. The missing information is in the values.
Corollary 1 gives the last.
(5) Test S<Nh before replacing a head, and search inside key-value groups first.