- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies whether failures to retrieve updated values reflect storage limitations or retrieval routing. It amplifies selected attention heads at the query position, improving latest-value retrieval, and combines these interventions with probes and representation analyses to explain apparent memory capacity.
Critical strengths
-
Query-only head amplification improves latest-value retrieval while preserving context representations. Random-head, wrong-position, and budget-matched controls strengthen the causal evidence.
-
Cross-model, cross-language, and surface-form transfer experiments show that the effect extends beyond a single model or prompt template.
Critical weaknesses
-
The causal interpretation is overstated. Amplification shows that selected heads can improve retrieval, but does not identify the original failure mechanism. The code-crowding explanation lacks positive intervention evidence, and all-position reverse ablation cannot establish storage-preserving bidirectional control.
-
Limited practical validation. Oracle deletion of stale entries simplifies the task using privileged information; its benefits cannot validate head amplification. The non-oracle intervention primarily strengthens recency bias, harms non-latest queries, and lacks consistent natural-task gains.
Questions for authors
-
Does Figure 4 support a broader memory-capacity claim, or only improved latest-value retrieval at the expense of access to earlier bindings?
-
Would the reverse transition persist under query-only ablation? Figure 38 uses all-position ablation, whereas §5 claims that both directions preserve the context.
-
Is the claim that interior access “must pay the crowding cost” justified, given that Appendix E.6 treats the geometry as descriptive and does not establish its causal role?
5 comments
Response to Reviewer vDaW 2/3
Weakness 1, the original failure
We agree that making a route stronger does not by itself show why it was weak, so we tested the failure side directly (Appendix N.6). We first measured how strongly each head pushes the answer toward each value at the query token. In Qwen3-1.7B the copy heads favor the latest value by a small margin, while four other heads favor older values at every load. The margin of the latest value over its strongest older competitor is negative and grows more negative with load, from -0.46 logits at u = 4 to -2.15 at u = 32. We then edited both sides of this competition at the query token only, with heads chosen on one set of prompts and every edit tested on new prompts.
| Accuracy at u = 8 (chance 0.13) | Qwen3-0.6B | Qwen3-1.7B | Pythia-2.8B | Qwen3-4B | Llama-3.1-8B |
|---|---|---|---|---|---|
| No edit | 0.22 | 0.24 | 0.42 | 0.14 | 0.18 |
| Remove four heads that favor older values | 0.41 | 0.51 | 0.61 | 0.15 | 0.22 |
| Remove four random heads (5 sets) | 0.22 | 0.24 | 0.42 | 0.13 | 0.19 |
| Remove four heads that favor the latest value | 0.07 | 0.18 | 0.28 | 0.10 | 0.14 |
| Amplify the heads that favor the latest value | 0.42 | 0.74 | 0.55 | 0.46 | 0.32 |
| Both edits | 0.37 | 0.88 | 0.76 | 0.45 | 0.35 |
In all five models, removing the heads that favor the latest value lowers accuracy or leaves it at the floor, and amplifying them raises it, while random heads stay within 0.02 of baseline on average. In Qwen3-0.6B, Qwen3-1.7B, and Pythia-2.8B, removing four heads that favor older values doubles accuracy at u = 16, and this gain holds with interleaved distractors and under free generation. In Llama-3.1-8B this effect is small, and in Qwen3-4B it is not reliable, so in these two models the pull toward older values is not concentrated in a few heads. The original failure is therefore a lost competition between two groups of heads at the query token, and in three of the five models the pull toward older values comes from a few heads that we can identify. We leave the earlier circuit that sets this balance to future work.
Weakness 1 and Question 3, the crowding explanation
We agree, and we have removed the claim that reading a middle value "must pay the crowding cost". We ran two new tests that could have given crowding a causal role. At a fixed load, the geometry of each prompt's stored order code does not predict whether the model succeeds on new prompts, with AUROC between 0.47 and 0.51. Spreading the order codes apart by a factor of 2 or 4, at one of five layers at a time, leaves accuracy at baseline (Appendix N.4). The paper now presents crowding as a description of the stored code throughout.
Proposition 1 keeps a narrower role in the revised paper. It limits what a read through the order code can deliver, and it predicts that heads which read by position alone reach only the first or the latest update. A new measurement finds that 68 to 93 percent of heads peak at one of these two ends (Appendix N.5). A new experiment also shows the way around this limit that the proposition allows (Appendix N.3). When each update carries its number, seven chat models read the middle value at 0.84 to 1.00 at u = 32, while six of them are at chance without numbers. The middle value is stored, and what these models lack is a way to find the n-th of several unlabeled mentions.
Response to Reviewer vDaW 3/3
Weakness 2, practical validation
We agree with you on both points, and we have changed how the paper presents eviction and the gain. Eviction shows that the latest value can still be recovered from the context, so we now present it as an upper bound and not as a validation of the gain. The gain is a causal probe of one retrieval route and not a ready-to-use fix. It has no effect on PI-LLM, where the baseline is already near zero, or on MultiWOZ, where interference is mild. When the query is a full sentence after the stream, the gain lowers latest accuracy from 0.24 to 0.14 at u = 8 and moves answers toward the first value instead. The gain is therefore tied to the query form that its heads were selected on.
We also ran the transfer test that a practical claim needs, with the heads, the gain, the task forms, the query wordings, and the controls all fixed in advance (Appendix N.7). The frozen gain lifts the code form under all three query wordings we tried, for example from 0.11 to 0.76 and from 0.30 to 0.56 at u = 8, and by more than both controls. It does not transfer to the dialogue and memo forms, where it lowers accuracy. Section 4.8 and the limitations now state these roles and limits. Within this scope we added two further results.
- The cost on other queries can be avoided. The prompt states the type of query, so a fixed text rule can apply the gain to latest queries only. By design this keeps every other query at baseline, and on Qwen3-1.7B at u = 8 it gives the best average over four query types (0.27, against 0.14 at baseline and 0.22 when the gain is always on).
- Two input formats that need no annotation show that the stored values can be told apart once the model has an address to match. On interleaved streams at u = 32, filtering the stream by the queried key raises Qwen3-1.7B from 0.04 to 0.42, although it does not help Qwen3-4B at that load. A version label on each update lets the same model read a middle version at 0.95, and Qwen3-4B at 0.99, although it helps much less for the latest version (0.24). Smaller models such as GPT-2-large do not use the label, so we report these formats as evidence about the mechanism rather than as a general fix.
Question 1, what Figure 4 supports
Figure 4 supports better retrieval of the latest value at the expense of access to earlier values, and not a broader claim about memory capacity. Section 4.7 now says this explicitly, and our capacity claims now concern retrieve-latest capacity only. We think this trade-off is the most informative part of the figure. A general improvement in memory would lift every query, while the gain lifts exactly one query and pulls every other query toward the latest value, which shows that it acts on a recency route and not on storage. The earlier values also remain stored, since an explicit number lets the same models read them.
Summary
Thank you again for these thoughtful and challenging points, which made the paper more careful and more convincing. The revision adds query-only tests of both directions of the switch, in GPT-2-large and in chat models, and a causal test of the original failure that holds strongly in three of five models. It also adds a transfer test fixed in advance that shows where the gain helps and where it does not. Finally, it adds direct tests of the crowding account, a numbered-update experiment, a rule that applies the gain only to latest queries, and input formats that need no annotation. We hope these results address your concerns, and we would be grateful if you would consider the new evidence. We are happy to answer any further questions.
Response to Reviewer vDaW 1/3
Thank you very much for your clear and constructive review. We are glad that you found the query-only amplification and its controls convincing, and that you saw the transfer across models, languages, and surface forms as a strength. Each of your concerns led us to run new experiments, and together they make the causal story both stronger and more precise. All new and changed text in the paper is shown in blue, and the new experiments are collected in Appendix N.
Weakness 1 and Question 2, the reverse transition with an edit at the query token only
The reverse transition holds when the heads are removed only at the query token. We repeated the GPT-2-large experiment with the same six copy heads removed only at the final query token, and we checked that every activation in the context stays exactly the same at every layer. Accuracy at u = 32 falls from 0.16 to 0.08 (chance is 0.03) and the curve meets the binding-limited criterion, while all 15 sets of random heads leave the model in the recency-copy regime. On 1,000 new prompts per load the result holds again, with accuracy falling from 0.12 to 0.07 (95 percent interval 0.06 to 0.09). On four more base models the query-only edit removes 42 to 91 percent of the endurance lost under the original edit (Appendix N.2).
Chat models show the same effect under their own chat templates (Appendix N.8). We selected heads on a separate set of prompts and removed them only at the final prompt token. In gemma-2-2B-it, which is far from the regime boundary, removing four heads lowers accuracy at u = 32 from 0.82 to 0.30, and in Qwen3-4B it falls from 0.58 to 0.09. Nine sets of four to sixteen random heads keep these two models at 0.76 or above and at 0.49 or above. When we instead remove the heads that hurt short streams the most, gemma-2-2B-it stays at 0.78 for u = 32, so the selected heads matter for long streams in particular. In gemma-2-2B-it and GPT-2-large the removed heads also leave accuracy on keys that appear only once almost unchanged, so in these models they carry the route that reads the latest of several updates. Qwen3-1.7B under its chat template is an exception to this. Qwen3-1.7B and gemma-3-4B-it, which are closer to the boundary under their templates, become binding-limited when two and four heads are removed.