arXiv Computation and Language

Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting

The paper investigates time‑incremental continued pretraining (CPT) of large language models using web‑scale data that overlaps across snapshots. Across six open‑weight models, CPT improves factual recall without catastrophic forgetting, while the cost is negligible and data quality outweighs quantity. The study identifies optimal learning rates, shows LoRA can match full CPT, and demonstrates that CPT gains transfer to fine‑tuned models.

arXiv AI

Sep 4

Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning

The paper introduces LRE (Learned Relevance Eviction), a lightweight, CPU‑only, language‑model‑free scorer that learns which parts of an agent’s interaction history are task‑critical and preserves them verbatim. In experiments, LRE matches or surpasses baseline eviction policies on accuracy‑cost trade‑offs, recovers 93% of full‑history accuracy, reduces worst‑case prompt size by 52%, and outperforms dense and token‑pruning encoders in conversational memory while being 295–1569× smaller. The method also achieves superior budgeted answer quality on LoCoMo reading and can be trained annotation‑free, recovering 95% of supervised scorer performance.

By Nusrat Jahan Lia, Aritra Mazumder

llms agents efficiency

arXiv AI

Aug 11

Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages

arXiv:2603. 12658v2 Announce Type: replace-cross Abstract: Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting, a critical limitation of the static pre-training paradigm inherent to modern LLMs.

By Hongyang Chen, Zhongwu Sun, Hongfei Ye, Kunchi Li, Xuemin Lin

llms fine-tuning benchmarks safety

arXiv Computation and Language

Aug 24

Index SLM Technical Report

arXiv:2607.09885v3 Announce Type: replace Abstract: We present Index-1.9B, a series of open small language models developed at Bilibili. The series comprises four models: Index-1.9B-Base, a foundatio...

By Tianjiao Li, Lusheng Zhang, Shien He, Xiaojing Liu, Tianxing Yan, Mengran Yu, Ziang Cui, Kai Zhao, Xipeng Wang, Yang Liu, Yuxin Li

llms rag fine-tuning benchmarks data-engineering

arXiv Machine Learning

Jul 20

Rethinking Transfer in Continual Learning: A Replay-Based Realisation

arXiv:2607. 15587v1 Announce Type: new Abstract: Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch.

By Yang Meng, Zhenya Liu, Zhuokai Zhao, Yuxin Chen

llms efficiency

arXiv Machine Learning

Jul 8

Fine-Tuning Regimes Define Distinct Continual Learning Problems

arXiv:2604. 21927v3 Announce Type: replace Abstract: Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge.

By Paul-Tiberiu Iordache, Elena Burceanu

fine-tuning benchmarks

arXiv AI

3d ago

Frozen Memory Is Not Enough: Rethinking External Memory as Extraction

arXiv:2608.17050v3 Announce Type: replace-cross Abstract: Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieval offers flexible access...

By Mingyuan Li, Guangsheng Yu, Xu Wang, Shaoxiong Ji

llms nlp safety

arXiv Machine Learning

4d ago

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?

arXiv:2609.37076v1 Announce Type: new Abstract: Large language models trained on vast corpora inherently risk memorizing harmful content that may later re-emerge in their outputs. To mitigate this is...

By Puning Yang, Qizhou Wang, Junchi Yu, Bo Han, Xiuying Chen

llms

arXiv Machine Learning

Sep 10

Continual Learning Mechanisms Compose for Long-Horizon Memorization

arXiv:2609.06986v1 Announce Type: new Abstract: Language models may need to internalize information that arrives over time and retain it through many subsequent updates. To study this challenge, we i...

By Zheyuan Zhang, Alvin Zhang, Daniel Khashabi, Tianmin Shu

llms fine-tuning

arXiv AI

Jun 30

Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management

arXiv:2606. 30067v1 Announce Type: cross Abstract: We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces.

By Byeong Hoon Yoon

rag fine-tuning efficiency benchmarks

arXiv AI

Jul 20

PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning

arXiv:2601. 13020v2 Announce Type: replace-cross Abstract: Continual instruction tuning (CIT) requires multimodal large language models (MLLMs) to adapt to a stream of tasks without forgetting prior capabilities.

By Zhiyan Hou, Haiyun Guo, Haokai Ma, Yandu Sun, Yonghui Yang, Jinqiao Wang

llms fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 10

When Does Continual Learning Require Learning

arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?

By Anne Harrington, Nayan Saxena, Michael Murphy, Anastasia Borovykh, Zeyu Yun, Sridhar Kamath, Ara Eindra Kyi, Trevor Darrell, Jitendra Malik, Yutong Bai

llms agents reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Aug 19

When to Review: Spaced Repetition for Continual Pre-Training of Language Models

The paper introduces Spaced Repetition Training (SRT), a continual learning framework that schedules sample rehearsal using the SM-2 algorithm. SRT tracks per-example review states and maps perplexity to recall quality, allowing the training loop to decide which examples to replay and when. Experiments on Wikipedia and code corpora show that SRT improves the stability‑plasticity trade‑off, recovers 5–37 percentage points of lost old‑knowledge accuracy, and preserves benchmark performance better than naive continual pre‑training or uniform replay.

By Alankar Atreya, Devesh Batra, Yoages Kumar Mantri, Geremy Bantug, Greig A Cowan, Raad Khraishi

llms benchmarks

Related stories