Continual Learning via Self-Probe Gradients

Dongkyu Cho; Rumi Chunara; Sungmin Cha

cs.LGSep 26, 2026

Continual Learning via Self-Probe Gradients

Authors: Dongkyu Cho, Rumi Chunara, Sungmin Cha

Organizations: New York University · Meta Reality Labs

Abstract

Adapting pretrained models to new data can cause catastrophic forgetting of previously learned behavior. When only a few past samples remain, they give continual learning methods sparse and narrow evidence about what to preserve. We show that language models can expand this evidence through self-probing, in which the frozen model generates new inputs from the retained samples and records its own predictions on them. Unlike prior work that replays such data as training examples, our method, CPLUS uses self-probe and past-sample gradients to scale down parameter updates that conflict with prior behavior. Experiments with five language models on four benchmarks show three results. First, the same probes preserve more prior behavior as gradient signals than as replay data. Second, CPLUS learns the new data while consistently reducing forgetting more than existing baselines, especially when past data are scarce, and this protection extends to benchmarks not used for training. Third, we observe that CPLUS also becomes more effective as models grow: within the Qwen3 model family, it recovers an increasing share of the forgetting caused by standard fine-tuning.

Figures & tables

Figure 1: Limited past-data access leaves preservation signals both sparse and narrow. (a) Preservation weakens when past samples are scarce. Qwen3-0.6B is adapted to new CommonsenseQA data. Replay, Collaborative Parameter Learning (CPL), and CPLUS (Ours) use

A

retained examples (anchors); supervised fine-tuning (SFT) uses only the new data. Retention is the percentage of initially correct examples that remain correct after adaptation (Correct

\rightarrow

Correct). It generally decreases as

A

shrinks, indicating increased forgetting. CPLUS achieves higher Retention across anchor budgets. (b) Preserving the anchored target task does not necessarily preserve performance elsewhere. After the same CommonsenseQA adaptation, we evaluate five benchmarks that are not used for adaptation or as anchors. Colored points report each task’s accuracy change from the base model, and diamonds report the five-task average. Points and error bars are means and standard errors over five seeds; all methods attain 100% Acquisition (Incorrect

\rightarrow

Correct) on CommonsenseQA. CPLUS remains closest to the base model across the profile.

Figure 2: Overview of CPLUS. 1. Self-probes. The frozen base model uses the limited anchors

\mathcal{P}_{A}

as in-context demonstrations to generate a self-probe bank

\mathcal{S}_{A}

. 2. Gradient blend. Gradients from the anchors and self-probes are blended into

\widehat{g}

. 3. Smooth Update Masking. The blended preservation gradient gates the optimizer’s proposed new-data update

\delta_{t}

parameter -wise, and the binary mask is smoothed by an exponential moving average. Finally, the smoothed mask is applied to

\delta_{t}

. Thus, self-probes supply preservation evidence rather than replay targets.

Figure 3: CPLUS reduces forgetting even with few past examples. Curves show CPLUS (Ours) , CPL , Replay , Self-Probe Replay , and SFT across anchor budgets. Retention is the percentage of initially correct examples that remain correct after adaptation (Correct

\rightarrow

Correct). Error bars show five-seed standard errors. Panels share a vertical scale within each model row. Off-scale MedQA SFT values are annotated in the 4B and Gemma rows.

Figure 4: CPLUS preserves broader performance on other tasks while learning new data. Panels show changes from the base model after ARC-C, MMLU, or MedQA adaptation. Diamonds are unweighted averages over benchmarks external to the adaptation task; in the ARC-C panel, its own point is excluded from that average. Points and error bars show means and standard errors over five seeds. Each panel has its own labeled vertical range.

Figure 6: CPLUS in limited-anchor sequential multi-task adaptation. Training follows CSQA

\to

ARC-C

\to

MMLU

\to

MedQA, carrying forward each checkpoint; MMLU thus inherits CSQA and ARC-C training. The CSQA checkpoint is shared. Curves show accuracy on all encountered tasks (mean and standard error, three seeds). Replay, CPL, and CPLUS use

A=8

anchors per past task.

Figure 7: CPLUS offers a favorable compute–Retention tradeoff across the evaluated model scales. On CommonsenseQA, the axes report Retention gain over SFT and training FLOPs relative to SFT (log scale). Preservation methods use eight anchors; SFT uses none. One-time preparation is excluded. App. E.12 gives the accounting and baseline definitions. Y-axis scales differ.

Figure 8: Early forgetting can be followed by recovery as training continues. Retention over epochs (left) and the Acquisition–Retention path (right) for a 25-epoch Qwen3-0.6B/CommonsenseQA diagnostic with eight anchors. The lines show epoch-level scores without uncertainty bands. This diagnostic is independent of the five-run comparison in Figure 3 . Filled markers indicate the first epoch reaching 100% Acquisition.

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

ID	Question	Location
E1	Does CPLUS reduce forgetting when anchors are limited?	Figures 3 and E.1
E2	Does preservation extend beyond the behavior represented by the anchors?	Figures 4 and E.10
E3	Are self-probes more effective as preservation gradients than as replay targets?	Figure 5
E4	Which CPLUS components and configurations matter?	Figures 5 and E.2
E5	Does CPLUS remain effective in the tested task sequence?	Figures 6 and E.9
E6	How do Acquisition, Retention, and computational cost evolve during adaptation?	Figures 7 and E.3

Appendix

Table 2: Experiment index.

Figure 9: Retention under limited anchor access across model scale. Retention denotes Correct

\rightarrow

Correct. We compare access-matched CPL and CPLUS with four anchors on MMLU and MedQA. Labels report the absolute Retention improvement of CPLUS over CPL; points and error bars show means and standard errors. Every setting attains 100% Acquisition (Incorrect

\rightarrow

Correct).

Figure 10: Model-scale perspective. Colored lines show individual benchmarks and the black line is their macro average. Retention denotes Correct

\rightarrow

Correct. Left: Retention after unconstrained fine-tuning, measuring each model’s native vulnerability to forgetting. Center: CPLUS Retention averaged over

A\in\{4,8\}

. Right: the fraction of SFT forgetting recovered by CPLUS, computed as

100(R_{\mathrm{CPLUS}}-R_{\mathrm{SFT}})/(100-R_{\mathrm{SFT}})

, with CPLUS Retention averaged over the same two values of

A

. Every CPLUS run in the fixed grid attains 100% Acquisition (Incorrect

\rightarrow

Correct). Because each model induces its own mastered and new-data sets, the right panel measures the share of each model’s available forgetting headroom that CPLUS recovers.

Figure 11: Development-only hyperparameter searches. Retention denotes Correct

\rightarrow

Correct. Left: Retention for two- and four-example in-context generation across sampling temperatures, evaluated with Qwen3-0.6B on CommonsenseQA at

A=4

and

N=512

. The selected configuration uses two examples and

T=0.8

. Right: Retention across

A\in\{4,8,16,32\}

for self-probe-only preservation, 75:25 blending, and equal-weight blending under a separate development protocol. Equal-weight blending is strongest at all four budgets. All runs achieve 100% Acquisition (Incorrect

\rightarrow

Correct).

Reduction	EMA	Retention (%)	Acquisition (%)
Mean	None	$81.11\pm 2.95$	100
Mean	0.9	$\mathbf{82.32\pm 0.64}$	100
CVaR	0.9	$77.40\pm 0.28$	100

Appendix

Table 3: Reference reduction and mask smoothing. Development results with

A=64

, averaged over three runs.

Figure 12: Epoch-level Acquisition–Retention dynamics under limited anchor access. We evaluate SFT, Replay, CPL, and CPLUS after every epoch over 25 epochs on Qwen3-0.6B and CommonsenseQA with

A=8

anchors and lr=1e-6 . Left and center show Retention and Acquisition over training; right traces the corresponding Acquisition–Retention path. Both Retention panels use the same vertical scale, labeled on the left. Per-epoch uncertainty is not shown. Filled markers identify the first epoch reaching 100% Acquisition.

Anchor composition		CommonsenseQA (%)
Base-correct	Base-wrong	Retention	Correction	Overall
8	0	83.49	13.42	40.15
6	2	81.34	21.24	44.16
4	4	80.62	23.16	45.07
2	6	80.38	20.80	43.52
0	8	80.86	23.45	45.35

Appendix

Table 4: Effect of anchor composition when adapting Qwen3-0.6B to MedQA with

A=8

ground-truth-labeled CommonsenseQA anchors. All rows obtain 100% MedQA Acquisition and 100% accuracy on the eight supplied anchors. Results use one seed.

Method	Acquisition (%)	Retention (%)	Overall accuracy (%)
SFT	98.97	21.77	69.53
Replay	100.00	12.68	66.70
CPL	42.63	9.57	30.02
CPLUS	98.97	39.00	76.09

Appendix

Table 5: Fixed aggressive-update stress test on Qwen3-0.6B and CommonsenseQA with

A=8

. Every method uses AdamW at lr=1e-5 for exactly 10 epochs, with no early stopping, epoch selection, or Acquisition filtering. Results are from seed 0.

Method	Matched property	Retention (%)	Acquisition (%)
Norm-matched SFT	Applied update norm	45.45	100
Randomized CPLUS mask	Per-tensor mask coefficients	47.13	100
CPLUS	Probe-informed coordinate placement	71.05	100

Appendix

Table 6: Matched update controls. Every row achieves 100% Acquisition. The randomized mask preserves CPLUS’s exact within-tensor coefficient multiset, while norm-matched SFT matches the norm of the update applied by CPLUS.

Figure 13: Instantaneous mask geometry under limited anchor access. CPL and CPLUS are audited at seven pre-update states in separate, matched Qwen3-0.6B CommonsenseQA runs with

A=8

. The horizontal axis counts training epochs already completed. Left: fraction of coordinates admitted by the diagnostic gradient-sign mask. Right: fraction of each method’s candidate AdamW update squared norm admitted by that mask. The CPLUS diagnostic uses its blended probe–anchor gradient before EMA smoothing. The audit is read-only; results use seed 0.

Figure 14: CPLUS need not recover the full-data mask. Each method is compared with its own full-data reference. CPL is closer at every budget despite lower Retention (Correct

\rightarrow

Correct), so mask similarity alone cannot explain CPLUS’s advantage. Coordinate-level masks appear in Figure 15 .

Figure 15: Coordinate-level view of the mask audit. We replay the same 678 proposed optimizer updates under controlled probe-side inputs. Left: each row shows the update-weighted mean CPLUS mask at one anchor budget; “Full” uses all 418 past examples. Columns are 512 pre-registered coordinates from a middle-layer MLP down-projection, ordered identically in every row. Purple indicates a suppressed update coefficient (0) and yellow a retained coefficient (1). Right: each method is compared with its own full-data reference mask—CPL with full-data CPL and CPLUS with full-data CPLUS. Agreement is update-energy weighted, and 1 denotes identical masks.

Method	After ARC-C	After MMLU	After MedQA
SFT	66.81	72.20	61.21
Replay	72.04	77.29	69.73
CPL	75.18	70.77	69.65
CPLUS	83.94	80.86	78.87

Appendix

Table 7: Average Task Accuracy during sequential multi-task learning. Each entry is the unweighted mean of absolute accuracy over all tasks encountered through the indicated stage, averaged across three seeds. Task-level standard errors are reported in Table 8 for the final stage and visualized throughout Figure 6 .

Method	CSQA	ARC-C	MMLU	MedQA	Average
SFT	$36.04\pm 0.51$	$53.78\pm 0.49$	$74.82\pm 0.44$	$80.19\pm 0.43$	61.21
Replay	$55.29\pm 0.49$	$63.86\pm 0.45$	$79.59\pm 0.41$	$80.19\pm 0.42$	69.73
CPL	$59.85\pm 0.47$	$62.60\pm 0.45$	$74.38\pm 0.42$	$81.77\pm 0.40$	69.65
CPLUS	$\mathbf{69.34\pm 0.46}$	$\mathbf{78.27\pm 0.44}$	$\mathbf{83.43\pm 0.44}$	$\mathbf{84.45\pm 0.42}$	78.87

Appendix

Table 8: Accuracy after the final sequential-learning stage. Following adaptation to MedQA, CPLUS achieves the highest accuracy on every task encountered in the sequence. The final Average Task Accuracy is the unweighted mean of the four absolute task accuracies. Values are means

\pm

standard errors across three seeds; the Average column is computed from the task means.

Figure 16: Base-normalized capability scores after adaptation. Each axis reports the post-adaptation score as a percentage of the corresponding base-model score. The dashed polygon marks the base-model level (100%); values above 100 indicate improvement. Raw score changes are shown in Figure 1 .

Figure 17: Method-matched mask agreement across transformer depth. Each cell reports update-weighted agreement for one layer and anchor budget. (a) CPL with $A$ anchors compared with CPL using all 418 past examples. (b) CPLUS with $A$ anchors compared with CPLUS using all 418 past examples under the same controlled probe inputs. The shared color scale ranges from zero to one.

Figure 18: Cross-reference comparison with full-data CPL. CPLUS masks are compared directly with the mask constructed by CPL from all 418 past examples. (a) Agreement for the pre-registered Layer-14 MLP down-projection. (b) Agreement across all transformer layers. This deliberately mismatched reference measures how differently CPLUS suppresses updates; it is not an oracle target for CPLUS.

Continual Learning for LLMs

Continual learning for large language models studies how models absorb new knowledge and skills while retaining previously learned capabilities.

See all 233 papers

Self-Preservation in Language Models
Oct 8, 2026Dongkyu Cho, Rumi Chunara, Ali BehrouzContinual Learning for LLMs Replay-Based Continual Learning
New York University · Google Research · Cornell University
Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
May 25, 2026Martin Marek, Dongkyu Cho, Shikai Qiu +3Continual Learning for LLMs LLM Fine-Tuning
New York University
Attribution-Guided Continual Learning for Large Language Models
May 6, 2026Yazheng Liu, Yuxuan Wan, Rui Xu +3Continual Learning for LLMs LLM Fine-Tuning
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · The Beijing University of Posts and Telecommunications, Beijing, China

Oct 8, 2026J/K move · Enter open · S save

Self-Preservation in Language Models

Dongkyu Cho, Rumi Chunara, Ali Behrouz

New York University · Google Research · Cornell University

Continual Learning for LLMs Replay-Based Continual Learning Catastrophic Forgetting

Open paper AskPDF arXiv

Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part of what a model knows, while forgetting can extend beyond them. Recent work shows that language models can supplement this limited evidence by generating useful replay without access to their original training data. This raises a question about self-preservation: can a model help choose preservation targets that protect its own capabilities more broadly? To study this question, we organize task descriptions and their examples into Task Banks, whose entries can be selected and combined to guide replay generation by a frozen model. Continual instruction tuning with Qwen models of varying sizes yields three findings. First, the new task and learning rate shape which prior capabilities degrade, while tracking previously correct answers reveals losses that average accuracy can conceal. Second, generated replay reduces forgetting on tasks outside the bank. Combining partial banks strengthens this protection, improving mean retention of previously correct answers over either bank alone across the tested sizes. Third, the model can also help choose replay targets: selection informed by the new task improves mean held-out retention over random selection at 4B, with similar new-task gains, although smaller models show no corresponding advantage. Under a fixed example budget, however, replacing new-task examples with replay improves preservation at the cost of smaller new-task gains. Together, these findings show that models can support broader self-preservation by generating replay data and, in some settings, choosing which tasks to replay.

Abstract

Continual Learning for LLMs

Explore similar work

Self-Preservation in Language Models

Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay

Attribution-Guided Continual Learning for Large Language Models