arXiv Machine Learning June 15, 2026 By Yan Hong, Kedong Xiu, Wei Li, Jun Lan, Huijia Zhu, Shuheng Zhou, Zhongcai Lyu, Weiqiang Wang, Jianfu Zhang

LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models

Read the original on arXiv Machine Learning →

arXiv:2606. 13709v1 Announce Type: cross Abstract: We study controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models, aiming to increase non-refusal target-response behavior while preserving general capability under a compact intervention footprint.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Computation and Language

Oct 19

SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors

arXiv:2610.22640v1 Announce Type: new Abstract: Model-editing backdoors aim to induce harmful responses under a trigger while preserving ordinary behavior on untriggered input. Recent model-editing a...

By Yutong Ke, Yansu Wang, Zeyu Zhang, Xihao Guo, Chongwen Zhao, Kaizhu Huang

llms diffusion multimodal benchmarks safety

arXiv Machine Learning

Jul 23

LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization

arXiv:2407. 00740v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are widely adopted in real-world applications, it has become critical to ensure LLMs satisfy safety constraints, such as non-toxicity and logical consistency, as well as task- and situation-specific constraints.

By Hye Ryung Son, Saehee Eom, Mooho Song, Jay-Yoon Lee

llms rag safety

arXiv AI

Jun 30

Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation

arXiv:2511. 05852v4 Announce Type: replace-cross Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs).

By Yinjie Cheng, Paul Youssef, Christin Seifert, J\"org Schl\"otterer, Zhixue Zhao

llms fine-tuning benchmarks safety

arXiv AI

Sep 16

Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation

arXiv:2609.16145v1 Announce Type: new Abstract: We study a practical question: can a small correction module fix errors in a frozen language model's outputs without degrading its base capabilities? W...

By Gautam Kishore

llms reinforcement-learning robotics fine-tuning benchmarks

arXiv Computation and Language

Sep 11

Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction

The paper presents a prompt-based method for minimal-edit grammatical error correction (GEC) that reduces overcorrection in large language models (LLMs). It introduces taxonomy-based instructions, batch prompting to regularize overcorrection, and LLM-assisted prompt optimization, achieving an $F_{0.5}$ score of 78.32 on BEA-2019 with Gemini 3.1-Pro. This approach narrows the performance gap to fine-tuned models while avoiding their infrastructure demands.

By Kateryna Karpo, Artem Chernodub

llms fine-tuning benchmarks

arXiv AI

Jul 3

Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing

arXiv:2607. 01978v1 Announce Type: new Abstract: Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors.

By Siyuan Li, Youyuan Zhang, Ruitong Liu, Junxi Wang, Jing Li

llms multimodal benchmarks

One email a morning, machine-written

Related stories

SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors

LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization

Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation

Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation

Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction

Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing