- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper studies unlabeled test-time adaptation for reasoning models and argues that reducing input next-token cross-entropy does not necessarily improve answer accuracy or preserve other capabilities. It proposes TTShift, which freezes the pretrained model and learns dataset-shared additive shifts at the Q/V projection outputs using only unlabeled target inputs. Experiments on Qwen3-8B-Base and Qwen3.5-4B-Base across seven reasoning tasks show that TTShift improves average accuracy over the base models and is more stable than Q/V LoRA across a wide learning-rate sweep. The paper also analyzes gradient agreement, shift formation, and how the learned Q/V translations affect attention computation.
Critical strengths
-
The paper identifies a useful failure mode of test-time adaptation. The experiments clearly show that lower input CE can coincide with worse target accuracy and larger off-target degradation, which motivates restricting the adaptation space.
-
The shared-shift result is simple and empirically interesting. TTShift uses far fewer trainable parameters than Q/V LoRA and shows a substantially broader positive operating region across learning rates, while often causing less damage to previously correct predictions.
Critical weaknesses
-
The evaluation is fully transductive. The same target questions are used for both adaptation and evaluation. It is therefore unclear whether TTShift learns a shift that generalizes within the target distribution, or mainly adapts to the specific evaluation inputs. A held-out target split would make the generalization claim much stronger.
-
The novelty relative to simpler shift/bias adaptation is not fully established. TTShift learns a dataset-shared additive vector at Q/V outputs, which is closely related in form to bias-only or representation-shift adaptation. The paper compares against LoRA, TLM, SLOT, and EATA, but lacks a tightly matched bias/shift baseline under the same objective and intervention locations. This makes it harder to isolate what is new about TTShift itself.
Questions for authors
-
Can you evaluate TTShift in a non-transductive setting, where the shift is learned on one unlabeled subset of the target distribution and evaluated on held-out target examples?
-
How does TTShift compare with a matched bias-only or simple representation-shift baseline using the same Q/V locations, optimization objective, and training budget?
-
Can you report multiple seeds for the main results? The Qwen3.5-4B gain is only +0.94 pp, and most reported results are single-seed point estimates.