- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
One can train different LoRA adapters corresponding to distinct tasks for the original backbone weights . This paper studies the effect of composing these weights () on safety failures, which are not captured by either the base model weights or the individual adaptations for any task . The paper highlights that composition can introduce new failures. Additionally, they study interventions involving adapter retraining with safety data and composition-weight scaling, showing that reducing composition-only failures does not necessarily reduce overall harmfulness or preserve task utility.
Critical strengths
- The paper highlights a practical risk in modular LLM deployment, individually evaluated LoRA adapters may exhibit previously unseen harmful behavior when composed (linearly) together.
- Extensive evaluation across model families and different task adapters.
Critical weaknesses
- Limited novelty and theoretical contribution. The main formalisation and Proposition 1 are straightforward set-theoretic consequences of the definition of composition-only failures.
- Unnecessarily complicated presentation with limited novel results. The paper is very difficult to follow, due to use of unnecessary definitions, terms and fragmented experimental discussions. I suspect heavy use of AI, making the presentation highly unnatural.
Despite the considerable length and number of evaluations, however, after reading the paper, I am left with three fairly intuitive findings:
-
Combining adapters can introduce new harmful responses.
-
Aggregate harmful-response rates can conceal these failure rates.
-
Adding safety data or reducing adapter weights can improve safety, sometimes at the expense of task utility.
All three findings are reasonable, but the paper does not offer much explanation beyond demonstrating them empirically.
Questions for authors
refer to the weaknesses
3 comments
Reply to Reviewer dU8v, part 2 of 2. W2: presentation, the three findings, explanation. (Part 1: W1.)
W2, "unnecessary definitions, terms and fragmented experimental discussions." We agree it was hard to follow. Changes: Table 6 (App. A) now lists, for each result, the adapters, requests, judge and references used; Sec. 3 is shorter; the Fig. 2 curves are labelled.
W2, "heavy use of AI." The AI Use Statement discloses AI help with writing; the scientific content is ours.
W2, "three fairly intuitive findings." is the composition-only rate: the share of requests on which the composition is harmful (both judges) while the base and every member are not. Dolly is the weak member; "plain" Dolly is retrained without refusal data, "repaired" with it ("safe" in Tables 4–5).
-
Composition adds failures that no member shows, and a trained partner adds more than a random one. On Qwen2.5-7B, adding a real task adapter to Dolly gives 0.074–0.111; adding a random update of the same norm gives 0.020–0.057 (Table 2). Real stays above random with two more Dolly seeds and on 375 fresh requests (Table 33). New: with six random draws per partner, each real pair exceeds every draw, and all 12 paired differences with the four new draws (+0.054 to +0.084) survive Holm correction (Table 37). Scope: of the 12 earlier cells, 10 survive Holm; the other two are the weakest Dolly seed with GSM8K and Alpaca. On Qwen2.5-14B and Phi-4 the excess depends on the partner (Table 31). A new Dolly seed alone gives up to 0.084 (Table 32), which overlaps the composition means, and a composition's failing set shifts about as much when it is reseeded (App. C.1); so we argue from the random-partner control, not seed noise. The revision no longer claims that mean harm "stays close" to the weak member's; it now states that the sign is not fixed: +0.067 on the 297 requests, +0.003 on fresh ones, negative for 5–6 adapters (Table 12, App. C.2).
-
A count of new failures can fall because a member got worse. counts only requests that the base and every member pass. Plain Dolly is more harmful, so fewer requests can count (84% to 59%): falls (0.104 to 0.062) while total harm rises (0.185 to 0.318; Table 4). An audit that reports only new failures would rank the more harmful model safer. Table 4 now reports the eligible share beside . Scope: this follows from the definition, and the revision no longer calls it a "reversal"; among eligible requests the rate does not change significantly (0.123 vs 0.105). On fresh requests the drop in is not significant, and on Qwen2.5-14B rises with harm.
-
Refusal-data repair lowers new failures and total harm and keeps the task gain; averaging leaves harm above the base. Repair on the DialogSum pair takes total harm from 0.168 to 0.054 and from 0.094 to 0.017 at 100% of the partner's task score (Table 5), and this pair replicates on Qwen2.5-14B and Phi-4 (Table 22). Averaging takes to at most 0.013 but leaves harm up to 0.077 (base at most 0.020; Table 16) and keeps 78–81% of DialogSum's gain. Scope: only DialogSum has a gain over the base to keep; the Alpaca pair does not replicate on the two other models; the 297 requests were evaluated before the interventions were designed. On fresh requests repair gives 0.023 [0.014, 0.033]: the upper end misses the 0.03 bound fixed in advance, and harm is twice the base. Repair raises over-refusal (8.9% of safe XSTest prompts vs 1.2% before; Table 21).
W2, "does not offer much explanation." The revision gives a partial explanation, not a mechanism (Sec. 5.1, Sec. 6): the weak member leaves some requests close to refusal, and a trained partner, unlike a random update of the same size or spectrum, turns more of them into failures. Four tests (Qwen2.5-7B unless stated):
- Not the size of the update. Real pairs give 0.074–0.111, 2.3–3.1× a random partner of the same norm (Table 2, App. L).
- Not its spectrum. A partner with the real one's singular values in random subspaces stays at 0.020–0.051, against 0.081–0.108; all differences exclude zero (Table 34).
- Which requests fail. Dolly's first-token refusal margin ranks which eligible requests a real partner tips (AUC 0.62–0.68, all intervals above 0.5); the base model's margin does not (0.52; Sec. 6).
- What the partner does. With a random partner the response opens with the same word as Dolly alone on 0.89–0.92 of requests; with a real partner on 0.26–0.43 (three models; Table 35).
Limits: the probe is modest; margins do not add across members (App. D.3). Negative result: restoring the refusal-direction coordinate, with the decision rule fixed in advance, did not remove the failures (mean 0.097 without it, 0.122 with it; Table 38), so we make no causal claim about that direction.
The revision now states each finding with its control and scope, and backs a partial explanation with four tests and a reported negative result.
I thank the authors for their response, I appreciate the experiments compared to the random updates, however I still beilieve the paper requires significant updates and share sentiments similar to reviewer vdnt. I will maintain my score.
Reply to Reviewer dU8v, part 1 of 2. W1: “limited novelty and theoretical contribution”. (Part 2: W2.)
Reply to Reviewer dU8v, part 1 of 2. W1: "limited novelty and theoretical contribution". (Part 2: W2.)
Short answer. The contribution is a measurement, with a control, that we did not find in the closest prior work. When separately trained task adapters are summed, the sum fails on requests that the base model and every member pass. On Qwen2.5-7B a trained partner adds two to three times as many such failures as a random update of the same size.
Theory. We agree: Proposition 1 is now a Remark (Sec. 3.4) and is not listed as a contribution.
The closest work (Hammoud et al., Findings of EMNLP 2024, is now cited):
Your three findings, set against that work.
"Combining adapters can introduce new harmful responses." New here: this happens for adapters that nobody designed to interact, and more than for a random update. CoLoRA shows it for adapters co-trained to be benign alone and comply together. Its own control, a colluding adapter merged with an unrelated benign one, does not reproduce the effect; it concludes that the degradation "depends on a specific interaction pattern rather than arising from arbitrary merging" (v2, Sec. 4.4). We measure that case. On Qwen2.5-7B each real pair gives 2.3–3.1× the composition-only rate of its norm-matched random partner (Table 2, App. L); a spectrum-matched random partner stays as low (Table 34). New run (Table 37): every real pair is above all six random draws, and all 12 paired differences with the four new draws remain significant after Holm correction. In an audit of judge-flagged events, all three readers confirmed 64 of 70: 25 of 25 for the Dolly-free compositions and 19 of 25 for the selected compositions containing Dolly, the weak adapter (Table 36).
"Aggregate harmful-response rates can conceal these failure rates." New here: the converse. A count of new failures can conceal a rise in total harm, because it counts only requests that no reference model fails. When the weak adapter is retrained without refusal data, the count falls (0.104 to 0.062) while total harm rises (0.185 to 0.318; Table 4). The works above report one rate per model; we found none that counts requests on which only the composition fails.
"Adding safety data or reducing adapter weights can improve safety, sometimes at the expense of task utility." New, as far as we found: the test on sums of task adapters. Prior repairs act on one fine-tune, and Gudipudi et al. (2025, now cited) observe over-refusal when fusing a safety adapter. On sums, averaging removes most composition-only failures but leaves harm above the base (Table 16). Retraining the weak member with refusal data lowers both (Tables 4, 5) but raises over-refusal (8.9% of safe XSTest prompts vs. 1.2% before; Table 21). Safe LoRA matches this repair on total harm (0.057 vs. 0.056; Table 20) with less over-refusal.
Scope. We propose no attack or defence. That summing updates raises total harm is expected from Qi et al.; a merge less safe than every source is in Hammoud et al. The excess over random partners is general on Qwen2.5-7B only; on Qwen2.5-14B and Phi-4 it depends on the partner (Table 31). The audit has no non-event rows, and one of its three readers is an author.
Sec. 1 contributions, verbatim:
On novelty, the revision establishes two results we did not find in the work above: on Qwen2.5-7B a trained partner adds more composition-only failures than a random update of equal norm or spectrum, and a count of new failures can fall while total harm rises.