REVIEW 21 cited by
Continual Learning for Large Language Models: A Survey
Not yet reviewed by Pith; the record is open.
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
read the original abstract
Large language models (LLMs) are not amenable to frequent re-training, due to high training costs arising from their massive scale. However, updates are necessary to endow LLMs with new skills and keep them up-to-date with rapidly evolving human knowledge. This paper surveys recent works on continual learning for LLMs. Due to the unique nature of LLMs, we catalog continue learning techniques in a novel multi-staged categorization scheme, involving continual pretraining, instruction tuning, and alignment. We contrast continual learning for LLMs with simpler adaptation methods used in smaller models, as well as with other enhancement strategies like retrieval-augmented generation and model editing. Moreover, informed by a discussion of benchmarks and evaluation, we identify several challenges and future work directions for this crucial task.
Forward citations
Cited by 21 Pith papers
-
MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
MasFACT transfers historical topology priors across tasks via Fused Gromov-Wasserstein optimal transport and PAC-Bayes conservative adaptation to reduce topology forgetting in continual multi-agent settings.
-
How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift
Task adaptation with SFT drifts LLM alignment substantially more than RLVR, and the drift shows up both in behavior and in internal representations.
-
ReCoLoRA: Spectrum-Aware Recursive Consolidation for Continual LLM Fine-Tuning
Spectrum-initialized LoRA with elbow ranks and recursive SVD consolidation of the effective weight beats rank-swept PEFT baselines on three of four 7–8B models in continual GLUE fine-tuning.
-
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
CAP-TTA triggers context-aware preconditioned LoRA updates on high bias-risk OOD prompts to reduce toxicity in LLM narrative generation while preserving fluency and avoiding catastrophic forgetting.
-
Bisecle: Binding and Separation in Continual Learning for Video Language Understanding
Bisecle reduces catastrophic forgetting and improves accuracy in sequential VideoQA learning using multi-directional auxiliary losses and contrastive prompt regularization.
-
Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
Table-r1 combines a layout-transformation self-supervised task and a mix-paradigm GRPO stage so 7B/8B models outperform other small-model table reasoners and approach GPT-4o-level accuracy.
-
Is Extending Modality The Right Path Towards Omni-Modality?
Fine-tuning LLMs on extra modalities improves some knowledge tasks but degrades reasoning and instruction-following; weighted model merging preserves language ability better than training one model on all modalities.
-
Pitfalls in Evaluating Language Model Forecasters
A systematic critique showing temporal leakage and extrapolation flaws can undermine claims that LLM forecasters match or beat humans.
-
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
Reducing churn in continual RL via C-CHAIN prevents NTK rank collapse and substantially improves learning across four benchmark suites.
-
Continual Learning in Transition
A tri-axial framework of When, Where, and How organizes the ongoing transition of continual learning from parameter-centric updates to system-level capability evolution.
-
A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI
The paper organizes persistent AI limitations into a five-part taxonomy of cognitive capability gaps and proposes a conceptual ACIA architecture and cognition-centric metrics, none of which are validated.
-
SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling
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.
-
Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
RL post-training forgets less than SFT because it trains on on-policy data; refreshing SFT data each epoch also reduces forgetting.
-
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
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.
-
Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
CorDA++ uses data-driven SVD to initialize LoRA adapters, adding per-layer covariance selection and rank allocation that reduce forgetting and speed convergence compared to LoRA, PiSSA, QLoRA, and other baselines.
-
A Systematic Review of Poisoning Attacks Against Large Language Models
A systematic review that organizes 65 LLM poisoning papers into a threat model with four attack specifications and generalized metrics.
-
Continual Speech Learning with Fused Speech Features
Gated fusion of frozen Whisper layers improves continual learning on six speech tasks, with the double-stage variant best overall.
-
Enhancing Multimodal Continual Instruction Tuning with BranchLoRA
BranchLoRA reduces catastrophic forgetting in multimodal continual instruction tuning by using a shared LoRA matrix, task-specific branches, frozen experts, and learned task keys.
-
Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
A survey that categorizes continual learning methods for generative models into architecture-based, regularization-based, and replay-based paradigms across four model families.
-
The Future of Continual Learning in the Era of Foundation Models: Three Key Directions
Continual learning should pivot from weight-update-based methods to continual compositionality and orchestration of foundation models and agents.
-
Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection
A test-time training method that fine-tunes LoRA adapters on verifier-selected high-confidence pseudo-labels, reporting large gains on math benchmarks, but evaluated on the same queries it adapts on.
Discussion (0). Sign in to comment.