- Rating
- 2(+1)
- Confidence
- 4(+1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper studies a token-triggered forgetting pattern in LLM unlearning. It observes that forget-target names attract attention and that forget representations lose effective rank. Models showing this pattern often leak information when the target name is absent from the query. The proposed remedy, EE-TNPO, uses disagreement between intermediate and final-layer predictions to reweight token-level unlearning losses. Experiments cover TOFU, RWKU, WMDP, and MUSE.
Critical strengths
- Evaluating queries without explicit target names is useful. Strong forgetting on name-cued questions does not necessarily imply that the same information cannot be recovered through descriptions or reverse queries. The paper makes this distinction explicit and supplements standard forgetting scores with name-leakage measurements, which helps expose failures that aggregate metrics may miss.
- EE-TNPO is a simple modification of an existing objective and shows meaningful improvements on the main TOFU setting. For example, under LoRA, name leakage falls from 65.0% with TNPO to 27.5%, while retain ES remains similar. The paper also includes controlled trigger injection, activation patching, and results over four independent TOFU runs. These provide useful evidence, although they do not fully establish the proposed mechanism.
Critical weaknesses
- The model coverage is outdated, especially for the central mechanistic analysis. The main TOFU experiments rely on Llama-2-7B-Chat from 2023, there is no comparable analysis on recent Llama, Qwen, or Gemma models. More importantly, an additional performance table does not establish that the same attention and rank-collapse mechanism appears in another model. Since the paper makes claims about how unlearning works, reproducing the mechanism across backbones matters more than simply adding another benchmark score.
- The baseline set is too limited for a paper proposing token reweighting. The experiments mainly compare against NPO, WGA, and TNPO. SatImp is discussed but not evaluated. The paper should also compare with Selective Unlearning from Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning (Wan et al., 2025) and ATWU from Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance (Yüce et al., 2026). These methods directly address token-level selection or weighting and are needed to establish the value of the early-exit signal. The comparison should cover trigger-free forgetting at matched retention levels, rather than only the selected configurations of three baselines.
- The novelty is limited, and the mechanistic evidence does not establish the full proposed explanation. Ren et al. (Keeping an eye on LLM unlearning: The hidden risk and remedy) already studied prompt tokens acting as unlearning signals. Examining what happens when those tokens are absent is a useful extension, but does not by itself establish a new mechanism. Appendix D.2 patches entire attention or MLP outputs. This shows that late-layer modules affect forgetting; it does not isolate whether attention to trigger tokens causes rank collapse, or whether that collapse causes forgetting. On the method side, EE-TNPO combines a DoLa-inspired layer-disagreement signal with existing TNPO. Without a more targeted causal test, the work remains an incremental combination of known observations and techniques
- The weighting rule does not distinguish factual importance from forget-specific importance. A large early-exit discrepancy indicates that predictions change across layers, but does not establish that the corresponding token should be forgotten rather than retained. The name-detection results in Table 4 do not resolve this distinction. There is also no comparison against simple entity-span weighting, shuffled weights, or another inexpensive token score to establish why JSD is needed. The MUSE-Books result exposes this limitation: EE-TNPO and TNPO both achieve an ES-Forget score of 0.79, but EE-TNPO reduces retain ROUGE-L from 65.97 to 57.19. The authors acknowledge the shared-entity issue, but it directly limits the proposed scoring rule and its claimed generality.
Questions for authors
- Does the proposed attention–rank-collapse pattern reproduce on newer backbones? Can the authors show both the mechanism and the effectiveness of EE-TNPO on recent Llama, Qwen, or Gemma models?
- Does EE-TNPO outperform SatImp, Selective Unlearning, and ATWU under comparable tuning budgets and matched retention levels, particularly on trigger-free queries?
- Can the authors intervene specifically on attention to trigger tokens, rather than replacing an entire module’s output, and measure the resulting changes in both effective rank and forgetting?
- Does early-exit weighting improve over simple entity-span weighting or shuffled weights under the same loss normalization and optimization settings? What evidence shows that the score identifies forget-specific information rather than broadly important factual tokens?
10 comments
Response to Reviewer iNLQ (2/7)
W1 & Q1 (continued) — Effectiveness of EE-TNPO on Llama-3.2
Setup. Same Llama-3.2-1B and 3B models as in the previous comment, unlearned with TNPO and EE-TNPO under identical settings (TOFU Forget10, 4 seeds).
Table R2. TNPO vs. EE-TNPO on Llama-3.2 (mean over 4 seeds; %). ES-F / ES-R = extraction strength on forget / retain QA. MU = model utility. NRR-F = share of the 20 name-seeking (trigger-free) forget questions answered with the author's name. NRR-Gap = the same rate on retain questions minus NRR-F. NS ES-Sim = extraction strength on the name-seeking questions.
| Setting | Method | ES-F ↓ | ES-R ↑ | MU ↑ | NRR-F ↓ | NRR-Gap ↑ | NS ES-Sim ↓ |
|---|---|---|---|---|---|---|---|
| 1B FT | TNPO | 4.38 | 66.48 | 57.79 | 17.50 | 54.80 | 27.2 |
| EE-TNPO | 4.64 | 68.75 | 59.78 | 3.75 | 60.82 | 13.5 | |
| 1B LoRA | TNPO | 3.28 | 77.71 | 59.20 | 25.00 | 53.42 | 39.0 |
| EE-TNPO | 3.26 | 77.57 | 60.89 | 3.75 | 73.41 | 18.0 | |
| 3B FT | TNPO | 4.42 | 75.02 | 65.15 | 23.75 | 56.83 | 28.2 |
| EE-TNPO | 4.30 | 76.23 | 65.69 | 11.25 | 70.76 | 16.7 | |
| 3B LoRA | TNPO | 3.43 | 89.58 | 66.18 | 30.00 | 59.21 | 26.0 |
| EE-TNPO | 3.50 | 90.04 | 66.49 | 20.00 | 70.11 | 23.7 |
(3) The trigger-free failure reproduces on Llama-3.2. TNPO brings ES-F to 3.3–4.4 (originally 70.6 / 89.0) yet still names the forget author in 17.5–30% of name-seeking questions.
(4) EE-TNPO reduces trigger-free leakage in all four settings, at no cost in retention. It lowers NRR-F and NS ES-Sim and has the larger NRR-Gap in every setting. Standard forgetting is unchanged (ES-F within 0.3 points of TNPO), MU is higher in all four settings, and ES-R is higher under FT and within 0.5 points under LoRA.
(5) Gemma was not run. It requires TOFU fine-tuning, the unlearning runs and all analyses from scratch, which did not fit the rebuttal period. The three added backbones are 2024 models.
We will add Tables R1 and R2 to the paper and state for which backbones and update types each signature holds.
Response to Reviewer iNLQ (3/7)
W2 & Q2 — Token-level baselines: search grids and tuning budgets
The submission compared EE-TNPO with NPO, WGA and TNPO at one configuration each; SatImp was discussed but not run, and, as the reviewer notes, the methods were not compared at matched retention or under comparable budgets. We added SatImp, Selective Unlearning and ATWU, tuned every method under the same rule, and compared them on trigger-free queries at matched retention. This comment gives the search grids, the selection rule and the budgets; the next one gives the results.
Setup. TOFU Forget10, Llama-2-7B-Chat. All methods except ATWU use LoRA with the same learning rate (5e-4), 10 epochs and batch size 32. Every run is evaluated at epochs 4, 6, 8 and 10, with 2 seeds.
Methods and search grids. Every grid contains the method's published or official setting.
- NPO, WGA, TNPO, EE-TNPO (the methods of the paper). NPO: . WGA: . TNPO and EE-TNPO: . The paper used , and . For EE-TNPO we search only and keep the early-exit layer at the paper's value.
- SatImp (Yang et al., 2025) weights each token loss by , where p is the current probability of the token. We use the official code and six settings of (, , retain coefficient): (5, 1, 1), (3, 1, 1), (5, 0.5, 1), (5, 0.1, 1), (5, 1, 0.1) and (5, 0.1, 0.1). They cover the setting of its paper (, ), the recommended in its README and the retain coefficient 0.1 of its code.
- Selective Unlearning (SU) (Wan et al., 2025) unlearns only the tokens on which a model that knows the forget data and a model that does not disagree by more than γ. As these two assistant models we use the original model and the TOFU Retain90 model, which was never trained on the forget authors. Such an oracle does not exist in practice, so this choice favours SU. With γ ∈ {0.5, 0.8, 0.9}, its original gradient-ascent form never reached the retention level required below (best ES-R 88.3). We therefore report SU-TNPO: SU's token mask inside the EE-TNPO loss, which differs from EE-TNPO only in how the tokens are selected, with .
- ATWU (Yüce et al., 2026) learns a token-importance scorer during unlearning. Its official code supports FT only, so it runs under its authors' protocol, and we search its budget parameter .
Selection rule (matched retention). The rule was fixed before the runs: for each method, among all (setting, epoch) checkpoints with extraction strength on retain QA (ES-R) ≥ 95, we take the one with the lowest NRR-F (share of the 20 name-seeking forget questions whose generated answer contains the author's name), averaged over the 2 seeds. The selected settings of EE-TNPO, TNPO, SatImp, SU-TNPO and ATWU were then retrained with 2 further seeds that played no part in the selection.
Table R3. Search budget and selected setting per method. Checkpoints compared = settings × 4 evaluated epochs. GPU-h = training time of all LoRA runs of the method (ATWU runs under FT and is not comparable).
| EE-TNPO | TNPO | NPO | WGA | ATWU | SatImp | SU-TNPO | |
|---|---|---|---|---|---|---|---|
| Settings searched | 3 | 3 | 3 | 3 | 3 | 6 | 9 |
| Checkpoints compared | 12 | 12 | 12 | 12 | 12 | 24 | 36 |
| Selected setting | 2, ep 10 | 2, ep 8 | 0.1, ep 10 | 3, ep 10 | 0.3, ep 10 | (5, 0.1, 0.1), ep 6 | 0.5, β 2, ep 6 |
| GPU-h | 0.78 | 0.75 | 0.72 | 0.47 | – | 1.09 | 2.08 |
(1) No baseline had a smaller search than EE-TNPO. EE-TNPO, TNPO, NPO, WGA and ATWU have 3 settings each. SatImp and SU-TNPO have 6 and 9, because we added settings to both for fairness: with their first three settings neither was competitive (numbers in the next comment).
(2) EE-TNPO uses no explicit knowledge about the dataset. Its weights are the disagreement between the model's own early-exit and final predictions, computed in the same forward pass. It needs no second model, no oracle and no entity list, whereas SU needs the Retain90 oracle (whose training cost is not counted above). The extra cost is one projection of a hidden state onto the vocabulary: +3.7% training time over TNPO (LoRA, median of 8 runs each), with no additional forward or backward pass.
Response to Reviewer iNLQ (1/7)
We greatly appreciate the detailed and critical review. We address each concern below. W/Q numbers follow the order of the review, and the revisions we mention will be updated in the Camera-ready PDF.
W1 & Q1 — Mechanism and effectiveness on newer backbones
In the submission, the three analyses of Sec. 3 (effective rank in Fig. 1b, attention to names in Fig. 3, name injection in Table 1 of the paper) were run on Llama-2-7B only, and Qwen2 (App. E.2) had only a performance table, which, as the reviewer notes, does not show that the same mechanism is present. We repeated the three analyses on Llama-3.2-1B, Llama-3.2-3B and Qwen2-7B (this comment) and evaluated EE-TNPO on Llama-3.2 (next comment).
Setup. Llama-3.2-1B and 3B are fine-tuned on TOFU and unlearned on Forget10 with the paper's hyperparameters; Qwen2-7B uses the checkpoints of App. E.2 (4 seeds each; cells are seed means). The same analysis code is used for all backbones. The three blocks of Table R1 report the three analyses.
Table R1. Sec. 3 signatures on four backbones (mean of 4 seeds). (a) Forget-rank drop minus retain-rank drop vs. the original model (pp; effective rank of hidden states). For each method and backbone, both drops are averaged over the 25% of layers with the largest forget-rank drop (8 of 32, 4 of 16, 7 of 28 layers; chosen once from the mean over 4 seeds and applied to every seed), so a collapse is counted wherever it occurs. Large = only the forget subspace collapses, ≈0 (including small negative values) = both change alike; compare within a backbone. (b) Attention to forget-author names ÷ attention to retain-author names (upper half of layers); 1 = equal. (c) ROUGE-L recall (%) on unrelated questions with a forget / retain author name inserted (Table 1 probe); a low first value next to an unchanged second one = the forget name alone triggers suppression.
(1) NPO-FT shows no name trigger on any backbone. Its forget and retain ranks change alike (difference −0.4 to 5.5 points), forget names receive almost no extra attention (1.01–1.14, against 0.95–0.98 in the original models), and inserting a forget name does not lower the score below that for a retain name (44.9–64.5 vs. 38.7–50.8).
(2) NPO-LoRA, TNPO-FT and TNPO-LoRA are triggered by the name on every backbone. In all three, forget names receive more attention than retain names (1.31–2.62), a forget name alone lowers the score below the retain-name score in every cell (by 10–49 points), and in all but one cell the forget rank drops at least 11 points more than the retain rank. TNPO-LoRA has the strongest rank and injection signatures on every backbone (rank 21–47; forget-name score 0.8–4.3). The two deviations are in strength, not in direction: NPO-LoRA has a weaker rank signature (11.5–26.6 on three backbones, 3.4 on Llama-3.2-1B), and TNPO-FT varies with the backbone, strong on Llama-2 and Llama-3.2-3B (rank 38.0 and 20.5; forget-name score 11.2 and 12.7) and weaker on Llama-3.2-1B and Qwen2 (rank 11.5 and 13.2; forget-name score 28.7 and 39.9).
In summary, the pattern of Sec. 3 holds on all four backbones: NPO under FT does not rely on the name, whereas TNPO and LoRA updates do. What varies with the backbone is the strength of the signatures under FT and the rank signature of NPO-LoRA.