← Back to all news
arXiv Machine Learning By Louis Robinson

Causal Edit Serialization

Read the original on arXiv Machine Learning →

Causal Edit Serialization (CES) is a framework that enables autoregressive language models to perform revisions—such as insertion, deletion, replacement, copying, and movement—within the same causal token stream. CES uses special pointer tokens paired with predicted source addresses, a lightweight localization head, and dual-index rotary position encoding to localize edits while preserving standard causal attention. Experiments show that CES models can execute complete edits with only a modest increase in clean-text bits per byte, and that post‑training with supervised or reinforcement learning can produce beneficial grammatical error corrections.

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.

Related stories

arXiv AI
Oct 12

AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits

AutoIndexer is a generative model that trains causal models on chains of edits, enabling flexible post‑generation modifications such as token insertions, substitutions, and deletions. It introduces marker tokens for opening and closing edits and moves a cursor through the token sequence, mimicking a text editor. By perturbing ground‑truth labels with inverse edit operations during training, AutoIndexer becomes robust to erroneous context and can perform editing tasks like code correction while maintaining performance on standard LLM benchmarks.

By Shu Ishida, Aliasghar Khani, Tianyu Zhang, The Cong Luong, James Seale Smith, Adam Gaier
llmsdiffusionbenchmarks
More like this →
arXiv Machine Learning
Jun 16

KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing

arXiv:2606. 17034v1 Announce Type: cross Abstract: Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached states of all subsequent tokens.

By Mufei Li, Shikun Liu, Dongqi Fu, Haoyu Wang, Yinglong Xia, Hong Li, Hong Yan, Pan Li
llmsfine-tuningefficiency
More like this →
arXiv AI
Sep 17

Contiguity, Not Importance: Budgeted Repair of Stale KV Caches After Document Edits

The paper investigates how to efficiently repair stale key-value (KV) caches in retrieval‑augmented generation systems after document edits. It proposes a budgeted in‑place recomputation approach and evaluates training‑free position‑selection policies on a factual RAG benchmark. Across three model families, a contiguous edit‑local window consistently recovers most of the post‑edit answer quality while being 13–21 times faster than a full re‑prefill, though its effectiveness diminishes when answer‑bearing text moves downstream.

By Mingyang Mao, Wyatt Mackey, Xiaomin Lin
ragagentsbenchmarks
More like this →