The paper investigates whether targeted edits to a few internal components of Gemma 4 instruction‑tuned models can reduce persistent repetition loops that occur during long factual enumeration prompts. By combining per‑layer ablation with per‑neuron attribution, the authors identify specific neurons whose weight edits dramatically lower loop frequency—one sign‑inverted neuron suffices for Gemma 4 E2B. Across all four Gemma variants, loop occurrences drop from 46/384 to 12/384 on held‑out prompts, while general‑purpose benchmarks show no significant regressions. The study also demonstrates that similar sparse edits can mitigate repetition in other families such as Qwen3.5 and LFM2.5, though the effect varies.
By Aristotelis Lazaridis, Aman Sharma, Dylan Bates, Brian King, Vincent Lu, Jack FitzGerald
arXiv:2609.38142v1 Announce Type: new
Abstract: A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advi...
By Rishabh Agrawal, Hejie Cui, Shasha Li, Shanchan Wu, Sercan \"{O}. Ar{\i}k
arXiv:2608.20873v1 Announce Type: new
Abstract: Every way of teaching a deployed language model something new -- full fine-tuning, adapter merging, model editing -- replaces the released checkpoint,...
By Zifeng Liu, Zhiyong Du, Yaxin Lu, Yiming Mao, Zhenhe Wang, Wenqi Shi, Zhengkun Jing
arXiv:2608. 04788v1 Announce Type: cross Abstract: Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated.
By Yi Yang, Cong Qin, Xiaodan Liu, Chishui Chen, Qing Dong, Yan Zhang, Cao Liu, Zhao Yang, Lu Pan, Jiaye Lin, Yi Feng
The paper investigates how sequential knowledge editing can degrade a language model’s ability to discern reliable evidence from unreliable evidence without affecting overall accuracy. Using a conservatively tuned LoRA on Qwen2.5‑7B‑Instruct, the authors show that after 1,000 edits the model’s arbitration score for untouched facts drops by 36%, leading to higher error rates on its most confident decisions, while MMLU accuracy remains unchanged. The study also finds that in some model‑method combinations, sequential edits can reduce MMLU to chance levels even though edit success and locality remain perfect.
By Atul Anand
arXiv:2606. 13705v1 Announce Type: cross Abstract: Yes.
By Aristotelis Lazaridis, Aman Sharma, Dylan Bates, Brian King, Vincent Lu, Jack FitzGerald
The paper investigates how memory systems can answer a current query correctly yet fail to retain distinctions needed for later updates. Using a paired‑history audit, the authors evaluate 24 history pairs across six synthetic mechanisms and two model backends, achieving perfect reveal accuracy on DeepSeek and high accuracy on GLM. Record‑level audits reveal specific failures in structured reveal memories and frontier late‑reference adequacy, and the authors test a label‑equivariant repair that only partially restores correctness.
By Guangzhe Zhang
arXiv:2604. 26866v2 Announce Type: replace-cross Abstract: Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction.
By Dimitris Dimakopoulos, Shay B. Cohen, Ioannis Konstas
ReDraft is a reference‑driven revision method for continual post‑training of large multimodal language models. It uses the model’s own incorrect outputs as references, revises them, verifies the revisions, and fine‑tunes on the accepted ones, thereby combining explicit supervision with policy proximity. On tasks such as Counting, Clock Reading, and Jigsaw, ReDraft outperforms standard supervised fine‑tuning and on‑policy methods, achieving higher target‑task gains while dramatically reducing forgetting.
By Zhihao Zhang, Mingqi Wu, Qiaole Dong, Enyu Zhou, Shuo Li, Boyang Liu, Jiazheng Zhang, Honglin Guo, Xin Guo, Shaofan Liu, Junzhe Wang, Dingwei Zhu, Zhiheng Xi, Minlong Peng, Yuan Hua, Qi Zhang, Tao Gui, Xuanjing Huang
arXiv:2608.20873v3 Announce Type: replace
Abstract: A 4-bit quantized weight specifies a rounding cell rather than a single full-precision value. We introduce in-cell learning, a paradigm for writing...
By Zifeng Liu, Yaxin Lu, Xuanhan Wu, Zhiyong Du, Yiming Mao, Zhenhe Wang, Wenqi Shi, Zhengkun Jing, Linwei Liu
arXiv:2609.36734v1 Announce Type: new
Abstract: Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implic...
By Ayan Sengupta, Vaibhav Seth, Tanmoy Chakraborty
arXiv:2609.37066v1 Announce Type: cross
Abstract: Post-training is central to mathematical reasoning in modern large language models (LLMs), but endpoint pass@1 alone underidentifies what has changed...
By Hongyang Li, Yiming Zhu, Xiao Li, Caesar Wu, Said Mammar, Pascal Bouvry