Pith. sign in

REVIEW 10 cited by

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.01244 v2 pith:DRI6FD43 submitted 2024-03-02 cs.CL cs.AI

Jianheng Huang , Leyang Cui , Ante Wang , Chengyi Yang , Xinting Liao , Linfeng Song , Junfeng Yao , Jinsong Su This is my paper
classification cs.CLcs.AI
keywords rehearsalsyntheticinstanceslearningabilitycatastrophiccontinualconventional
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) suffer from catastrophic forgetting during continual learning. Conventional rehearsal-based methods rely on previous training data to retain the model's ability, which may not be feasible in real-world applications. When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent. To address this challenge, we propose a framework called Self-Synthesized Rehearsal (SSR) that uses the LLM to generate synthetic instances for rehearsal. Concretely, we first employ the base LLM for in-context learning to generate synthetic instances. Subsequently, we utilize the latest LLM to refine the instance outputs based on the synthetic inputs, preserving its acquired ability. Finally, we select diverse high-quality synthetic instances for rehearsal in future stages. Experimental results demonstrate that SSR achieves superior or comparable performance compared to conventional rehearsal-based approaches while being more data-efficient. Besides, SSR effectively preserves the generalization capabilities of LLMs in general domains.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    Boundary-aware Curriculum RL raises average pass@256 by 9.8 points over base models and 10.3 points over vanilla RLVR on Qwen, Llama, and DeepSeek families.

  2. Robust Policy Optimization to Prevent Catastrophic Forgetting

    cs.LG 2026-02 unverdicted novelty 6.0 of 10

    FRPO applies a max-min robust optimization over KL-bounded policy neighborhoods during RLHF to reduce catastrophic forgetting of safety and accuracy under subsequent SFT or RL fine-tuning.

  3. SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling

    cs.LG 2026-06 conditional novelty 5.0 of 10

    A LoRA update split into several fixed, differently-scaled low-rank experts with orthogonal input directions improves fine-tuning accuracy at the same parameter count.

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

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Self-generated replay from language models nearly eliminates catastrophic forgetting during finetuning except when models are pretrained close to saturation.

  5. Memento: Personalized RAG-Style Long-Retention Data Scaling for META Ads Recommendation

    cs.IR 2026-05 unverdicted novelty 5.0 of 10

    Memento applies personalized RAG-style retrieval to long user history for Meta ads models, delivering 5-10x efficiency, sub-10ms latency, and 1% CTR / 1.2% CVR lifts in production.

  6. SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment

    cs.CL 2025-09 conditional novelty 5.0 of 10

    Adding a KL penalty between fine-tuned and original model logits on input tokens during RAG fine-tuning reduces catastrophic forgetting while preserving downstream performance.

  7. CLaaS: Continual learning as a service for sample efficient online learning

    cs.LG 2026-06 unverdicted novelty 4.0 of 10

    CLaaS enables sample-efficient online continual learning for agents via replay-buffered parametric updates, outperforming in-context learning in forward transfer and retention on an adversarial task.

  8. Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning

    cs.LG 2025-09 conditional novelty 4.0 of 10

    FAPM prunes task vectors using a combined absolute and relative change magnitude criterion, reducing forgetting on general benchmarks to roughly a third of a percent while keeping downstream accuracy near the fine-tun...

  9. Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach

    cs.LG 2025-08 reject novelty 4.0 of 10

    Gauss-Tin, a replay method using a Gaussian mixture model with prompt-guided exemplar selection, reports positive backward transfer on the Natural Instructions benchmark versus sequential fine-tuning.

  10. Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead

    cs.SE 2025-06 conditional novelty 4.0 of 10

    A literature review organizes LLM development into a six-phase software engineering lifecycle and identifies challenges and research directions for each phase.

Pith tools