- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper attributes difficulties in refusal steering to dominant CoT-progress variation and comparatively weak behavioral signals. It proposes SubSteer, combining pre-decision direction extraction, progress-dependent intervention strength, and multi-layer steering, and evaluates it across four reasoning models and additional behavioral tasks.
Critical strengths
- Effective steering. SubSteer improves bidirectional refusal control over several existing methods. Extracting directions at the pre-decision boundary and distributing stage-dependent interventions across layers provides a concrete approach to balancing steering success and CoT completion.
- Relevant comparisons. The evaluation includes five steering baselines, four model families, and ablations of direction extraction, strength adaptation, and layer distribution. These comparisons provide useful evidence for the contribution of the proposed components.
Critical weaknesses
- Incomplete causal explanation. The geometric measurements establish differences in signal scale, but do not establish that progress dominance causes steering failures. Improved completion under smaller, distributed interventions could also reflect generic benefits of limiting perturbation magnitude, rather than preservation of a specific progress representation.
- Insufficient quality assessment. Producing an end-of-thinking token within the budget does not establish coherent or effective reasoning. The claim of preserving CoT quality requires evaluation beyond termination, including reasoning performance and benign-task utility. Substantial unclosed rates also remain on Qwen3.5-9B.
- Unclear need for progress estimation. The fixed-strength ablation supports adaptive intervention, but does not establish the necessity of activation-based progress estimation. A simpler token-count-based schedule, matched for direction, layers, and intervention budget, would clarify the added value of the proposed calibration.
Questions for authors
- Can the authors use finer-grained annotations of reasoning stages, such as problem analysis, derivation, and verification, to clarify what the estimated progress bins actually represent?
- Can the authors directly test whether disruption of the progress representation explains steering failures, rather than generic sensitivity to large activation perturbations?
- Does activation-based progress estimation outperform a simple token-count-based intervention schedule under matched settings?
- Does SubSteer preserve reasoning performance and benign-task utility, beyond allowing the CoT to terminate?
5 comments
Author Response to WS2G (Part 2/3)
Q2: Can the authors directly test whether disruption of the progress representation explains steering failures, rather than generic sensitivity to large activation perturbations?
… do not establish that progress dominance causes steering failures. Improved completion … could also reflect generic benefits of limiting perturbation magnitude, rather than preservation of a specific progress representation.
CoT-Progress Dominance and Steering Failures
We conduct additional activation-level analyses and controlled interventions to support the claim that SubSteer preserves the dominant progress structure.
We collect activations under SubSteer and single-layer intervention (). Following Section 3.2, we divide each CoT into ten bins according to relative token positions, average the activations within each bin, and connect the resulting mean activations to construct a trajectory. We visualize these trajectories using the two-dimensional space spanned by and . We have updated the trajectory visualizations in the revised paper in Appendix H.
Using these activation trajectories, we quantify how far LRMs move along the reasoning-progress direction under steering. Specifically, we measure the total movement of the mean CoT trajectory along across the ten stages. This metric directly tests whether the dominant progress representation is normally expressed under intervention.
As shown in the table below, SubSteer retains a larger progress range on average than single-layer steering, indicating that distributing the intervention preserves normal progression along . In contrast, single-layer steering severely influences the dominant progress representation, demonstrating that strong steering in a single layer disrupts this progress structure and stalls CoT completion (65.50% unclosed rate vs. 7.50% for SubSteer).
| Metric | Qwen3-8B | DeepSeek-8B | Qwen3.5-9B | GPT-OSS-20B |
|---|---|---|---|---|
| SubSteer: progress range of mean trajectory | 23.63 | 2.59 | 12.60 | 1952.19 |
| Single-layer: progress range of mean trajectory | 11.34 | 2.78 | 6.25 | 410.55 |
| Progress range ratio (Single-layer / SubSteer) |
We further examine whether simply reducing single-layer intervention strength can recover comparable steering effectiveness in the following table. Each entry reports Refusal Success Rate / CoT Unclosed Rate (S / U). We reduce its strength to achieve a similar progress range to SubSteer. Under this setting, single-layer steering becomes substantially less effective, achieving an average Refusal Success Rate of only 54.00%, compared with 92.25% for SubSteer. In fact, as shown in the strength-sweep experiment above, single-layer steering suffers from both CoT non-closure and steering failures even at its optimal intervention strength.
| Qwen3-8B | DeepSeek-8B | Qwen3.5-9B | GPT-OSS-20B |
|---|---|---|---|
| 0.46 / 0.02 | 0.26 / 0.00 | 0.57 / 0.29 | 0.87 / 0.02 |
Together, these results suggest that SubSteer's distributed interventions achieve a more favorable balance between behavioral control and preservation of progress-related representations.
Q3: Does activation-based progress estimation outperform a simple token-count-based intervention schedule under matched settings?
Token-Count-Based Progress Estimation
Unclear need for progress estimation…
A fundamental limitation of token-count-based scheduling is that the final CoT length is unknown during generation and may itself change under steering. Moreover, CoT lengths vary substantially across prompts, making absolute token positions an imperfect estimation for internal reasoning progress.
We introduce a token-count-based variant calibrated on unsteered training CoTs. Specifically, we fit a mapping from the number of generated CoT tokens to the current reasoning stages using harmful and harmless prompts. During steering, we use this mapping to control steering strength from the current token count.
The results show that SubSteer outperforms the token-count-based schedule with a higher average Success Rate (80.63% vs. 63.50%) and a lower CoT Unclosed Rate (10.38% vs. 16.88%), demonstrating the advantage of activation-based progress estimation for steering.
| Model | Target | Refusal Rate | Compliance Rate | CoT Unclosed Rate |
|---|---|---|---|---|
| Qwen3-8B | Refusal | 0.90 | 0.09 | 0.01 |
| Qwen3-8B | Compliance | 0.38 | 0.62 | 0.00 |
| DeepSeek-8B | Refusal | 0.53 | 0.05 | 0.42 |
| DeepSeek-8B | Compliance | 0.45 | 0.54 | 0.01 |
| Qwen3.5-9B | Refusal | 0.68 | 0.00 | 0.32 |
| Qwen3.5-9B | Compliance | 0.44 | 0.25 | 0.31 |
| GPT-OSS-20B | Refusal | 1.00 | 0.00 | 0.00 |
| GPT-OSS-20B | Compliance | 0.16 | 0.56 | 0.28 |
Author Response to WS2G (Part 3/3)
Q4: Does SubSteer preserve reasoning performance and benign-task utility, beyond allowing the CoT to terminate?
Producing an end-of-thinking token within the budget does not establish coherent or effective reasoning. ... Substantial unclosed rates also remain on Qwen3.5-9B.
We thank the reviewer for highlighting the need for a more comprehensive quality assessment. We address this concern from three perspectives: (1) CoT coherence, (2) the impact of steering on benign-task, and (3) the specific challenges observed with Qwen3.5-9B.
CoT Coherence
Meaning of Coherent. We focus more on whether the CoT remains non-empty, terminates naturally, and avoids obvious repetition, while overlooking the logical correctness of individual reasoning steps, because behavioral steering should ensure the model to complete its reasoning naturally and exhibit the intended steering behavior that may be inappropriate for the prompt.
Repetition Detection. We conducted an additional 4-gram repetition analysis on the SubSteer’s CoTs. Specifically, we measure the proportion of repeated occurrences of contiguous four-word sequences (4-grams) within each CoT, and classify CoTs with a repetition rate above 30% as highly repetitive,
=1-\frac{\text{Unique4grams}}{\text{All4grams}}.$$ Across all four models and steering targets, we found no empty CoTs and only 9 (1.2%) highly repetitive examples, all occurring under compliance steering on Qwen3.5-9B and GPT-OSS-20B. **Human Review.** We additionally conducted a blinded human evaluation of 100 randomly sampled CoTs (excluding 9 identified repetitive cases). The inspection found no empty or visibly degenerate reasoning traces among these samples. Together, these results provide further evidence that SubSteer generally maintains generation-level CoT coherence beyond simply producing an end-of-thinking token. We clarify this definition and add the repetition analysis and human evaluation results to the appendix. ### **Impact on Benign-Task Utility** Our study investigates how behavioral decisions can be steered during the CoT reasoning process of LRMs. Importantly, it performs unconditional behavioral steering, applying the steering to all inputs to force refusal or compliance, which inevitably leads to incorrect reasoning in some CoTs. We hope that SubSteer could inspire future work for better LRM defense without CoT degradation. To quantify this effect, we evaluate SubSteer on benign reasoning tasks (50 GSM8K and 50 MATH-500 math tasks) and over-refusal benchmarks (50 XSTest and 50 WildJailbreak adversarial-benign prompts). Overall, the results demonstrate that SubSteer shifts model behavior toward the targeted direction on benign prompts. **Benign Dataset.** The table below reports SubSteer’s impact on mathematical reasoning. As expected, the refusal rate of positive refusal steering increases from 0% to 20.25%, while the average reasoning accuracy decreases from 88.50% to 68.25%. Subtractive steering maintains comparable reasoning accuracy to the unsteered models (88.25% vs. 88.50%). |Model|Method|Refusal|Correct|Closed and Incorrect|Unclosed| |---|---|---:|---:|---:|---:| |**Qwen3-8B**|Baseline|0.00|0.88|0.00|0.12| ||Add|0.40|0.45|0.00|0.15| ||Subtract|0.00|0.90|0.02|0.08| |**DeepSeek-8B**|Baseline|0.00|0.74|0.16|0.10| ||Add|0.13|0.70|0.06|0.11| ||Subtract|0.00|0.76|0.17|0.07| |**Qwen3.5-9B**|Baseline|0.00|0.97|0.01|0.02| ||Add|0.01|0.90|0.02|0.07| ||Subtract|0.00|0.95|0.00|0.05| |**GPT-OSS-20B**|Baseline|0.00|0.95|0.03|0.02| ||Add|0.27|0.68|0.05|0.00| ||Subtract|0.00|0.92|0.02|0.06| The table below reports over-refusal results on XSTest and WildJailbreak adversarial-benign prompts. Entries report **Refusal rate / Unclosed rate**. The over-refusal rate on XSTest and WildJailbreak increases from 8.50% to 30.50% when positive refusal steering is applied. Conversely, subtractive steering reduces the over-refusal rate to 2.00%. | Model | Baseline | Add | Subtract | |---|---|---|---| | Qwen3-8B | 0.03 / 0.02 | 0.28 / 0.02 | 0.00 / 0.00 | | DeepSeek-8B | 0.04 / 0.01 | 0.08 / 0.00 | 0.02 / 0.00 | | Qwen3.5-9B | 0.08 / 0.11 | 0.19 / 0.35 | 0.04 / 0.14 | | GPT-OSS-20B | 0.19 / 0.05 | 0.67 / 0.00 | 0.02 / 0.18 | ### **Specific Challenges on Qwen3.5-9B** Qwen3.5-9B is the most challenging model in our evaluation. Even without steering, it exhibits a substantially higher CoT-unclosed rate and longer reasoning traces than the other models. This behavior is consistent with recent independent research on Qwen3.5 models [6, 7]. We have expanded the Discussion with these observations. [6] Alexander Boesgaard Lorup. Concise-9B: Removing the Slack from a Reasoning Model's Thinking. arXiv:2611.02278, 2026. [7] hyq-hub. High Parse Failure Rate (~13%) on Video-MME due to Repetitive Output Loops (Qwen3.5-9B). QwenLM/Qwen3.8, GitHub Discussion #124, 2026.
Author Response to WS2G (Part 1/3)
Q1: Can the authors use finer-grained annotations of reasoning stages, such as problem analysis, derivation, and verification, to clarify what the estimated progress bins actually represent?
The reasoning stages in our analysis are defined by relative token position and usually does not refer to a specific reasoning activity but a coarse reasoning progress. This is because one reasoning activity may happen in different reasoning stages across models.
To demonstrate this, we analyze CoTs generated from harmful and harmless prompts and report the distribution of reasoning activities across ten relative token-position bins. The following table reports some of the common activities. The results show that many reasoning activities occur at multiple stages. For example, problem analysis appears across the first 80% of CoT progression.
The position of the same activity also varies across prompts and models. For example, in Qwen3.5-9B, 43.71% of the self-examination activity occurs in the 10–20% interval for harmful prompts, but only 0.26% for harmless prompts.