Pith. sign in

REVIEW 4 cited by

Reinforced Lifelong Editing for Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.05759 v4 pith:6TUV7273 submitted 2025-02-09 cs.CL

Zherui Li , Houcheng Jiang , Hao Chen , Baolong Bi , Zhenhong Zhou , Fei Sun , Junfeng Fang , Xiang Wang This is my paper · ORCID
classification cs.CL
keywords editinglifelongparametersrleditapproachesgenerateknowledgelanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time. Model editing addresses this challenge by modifying model parameters without retraining, and prevalent approaches leverage hypernetworks to generate these parameter updates. However, they face significant challenges in lifelong editing due to their incompatibility with LLM parameters that dynamically change during the editing process. To address this, we observed that hypernetwork-based lifelong editing aligns with reinforcement learning modeling and proposed RLEdit, an RL-based editing method. By treating editing losses as rewards and optimizing hypernetwork parameters at the full knowledge sequence level, we enable it to precisely capture LLM changes and generate appropriate parameter updates. Our extensive empirical evaluation across several LLMs demonstrates that RLEdit outperforms existing methods in lifelong editing with superior effectiveness and efficiency, achieving a 59.24% improvement while requiring only 2.11% of the time compared to most approaches. Our code is available at: https://github.com/zhrli324/RLEdit.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models

    cs.CL 2026-07 conditional novelty 6.0 of 10

    ForgetBench is a sequential-editing benchmark showing that existing knowledge-editing methods trade long-term retention against generalization, while structured contexts mask parametric forgetting.

  2. Targeted Recovery of Weight-Space Mechanisms From Neural Networks

    cs.LG 2026-06 conditional novelty 6.0 of 10

    A targeted decomposition method recovers the weight-space mechanisms behind specific inputs at low FLOPs, enabling focused ablation and rewiring of a 12-block transformer.

  3. PropMEND: Hypernetworks for Knowledge Propagation in LLMs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    PropMEND meta-trains a gradient-editing hypernetwork with propagation questions as the outer-loop objective, improving multi-hop knowledge propagation in LLMs in-domain but generalizing poorly to unseen relations.

  4. From Construction to Injection: Edit-Based Fingerprints for Large Language Models

    cs.CL 2025-09 conditional novelty 5.0 of 10

    A three-stage LLM fingerprinting pipeline (multilingual low-perplexity triggers, edit-based injection with adversarial suppression, and subspace-aware fine-tuning regularization) reports robust and persistent ownershi...

Pith tools