The paper introduces Skill Schema Transport (SST), a post‑training framework that mitigates catastrophic forgetting in continual domain adaptation by translating new domain knowledge into a model’s existing skill space. SST abstracts each example type into a reusable skill schema, preserving essential operations while removing domain‑specific surface forms, thereby turning knowledge updates into procedural reuse rather than trajectory memorization. Experiments on two 3B instruction‑tuned backbones show that SST consistently reduces forgetting and improves generalization, achieving up to a 5.75‑point performance gain and a dramatic drop in maximum forgetting from 42.41 to 7.10 points on the Qwen‑3B MATH stream.
By Zijie Liu, Zhen Tan, Charles Fleming, Tianlong Chen
arXiv:2505.19893v2 Announce Type: replace
Abstract: Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce E...
By Melis Ilayda Bal, Volkan Cevher, Michael Muehlebach
arXiv:2607. 22769v1 Announce Type: cross Abstract: The training efficacy of large language models (LLMs) is fundamentally constrained by the quality and composition of training data.
By He Zhang
The paper investigates how synthetic tasks influence language‑model pretraining by distinguishing diagnostic, teachable, and transferable signals. In a controlled setting where 70% of the data is general Python and 30% is a mixture of curated synthetic tasks, literature‑derived probes, and OpenCodeInstruct, 14 of 27 tasks show teachability, with curated tasks outperforming literature probes. Curated synthetic data provides conditional value: it boosts downstream performance when mixed with OpenCodeInstruct but is less effective when used alone, and a loss‑based scheduler can misalign short‑term loss reduction with long‑term transfer.
By Ohad Rubin
arXiv:2608. 14071v1 Announce Type: new Abstract: As large language models scale, their training-token budgets must also increase to maintain an appropriate tokens-per-parameter ratio (\(\mathrm{TPP}\)).
By Jingwei Li, Xinran Gu, Rui Dai, Xintong Hao, Chengyin Xu, Yan Wu, Shuran Zheng, Jingzhao Zhang
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
arXiv:2607. 11052v1 Announce Type: new Abstract: Machine learning progress is often attributed to scaling model size and dataset volume, yet the composition of data can be just as consequential.
By Kimia Hamidieh, Lester Mackey, David Alvarez-Melis
The paper introduces a Fisher-guided submodular data selection method for continual pre‑training of large language models, addressing the forgetting problem that arises when a target‑domain corpus overwrites pretrained knowledge. By decomposing candidate gradients into anchor and frontier components and optimizing a log‑determinant submodular objective, the method selects data that both improves target‑domain performance and limits forgetting. Experiments on TinyLlama‑1.1B and Llama‑3.1‑8B show that the selector achieves superior adaptation and forgetting control while using ten times fewer tokens than traditional replay strategies.
By Zhenghao Zhao, Gaowen Liu, Zhiling Lan, Yan Yan
arXiv:2609.37169v1 Announce Type: cross
Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since add...
By Zhehao Huang, Changxin Tian, Qingyuan Yang, Kunlong Chen, Ziqi Liu, Zhiqiang Zhang, Xiaolin Huang, Jun Zhou
The paper introduces SynPro, a synthetic data generation framework that augments limited organic text for large language model pretraining by applying rephrasing and reformatting operations. SynPro’s generators are optimized with reinforcement learning rewards for quality, faithfulness, and data influence, and are updated continuously as training plateaus. Experiments on 400M, 1.1B, and 2B models show that SynPro can unlock 3.4–5.2× the effective tokens of standard repetition, even outperforming a non‑data‑bound oracle at larger scales.
By Zichun Yu, Chenyan Xiong
arXiv:2606. 05165v1 Announce Type: new Abstract: Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data.
By Rishit Dagli, Abir Harrasse, Luke Zhang, Florent Draye, Amirali Abdullah, Bernhard Sch\"olkopf, Zhijing Jin
arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
By Vin\'icius Conte Turani, Ot\'avio Parraga, Jo\~ao Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinsk\"u