Pith. sign in

REVIEW 2 cited by

Should We Really Edit Language Models? On the Evaluation of Edited Language Models

Not yet reviewed by Pith; the record is open.

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 2410.18785 v1 pith:XAF4P3CD submitted 2024-10-24 cs.AI

classification cs.AI
keywords editingmethodsmodelslanguagemodelknowledgegeneralabilities
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelling across these criteria. Some recent works disclose the pitfalls of these editing methods such as knowledge distortion or conflict. However, the general abilities of post-edited language models remain unexplored. In this paper, we perform a comprehensive evaluation on various editing methods and different language models, and have following findings. (1) Existing editing methods lead to inevitable performance deterioration on general benchmarks, indicating that existing editing methods maintain the general abilities of the model within only a few dozen edits. When the number of edits is slightly large, the intrinsic knowledge structure of the model is disrupted or even completely damaged. (2) Instruction-tuned models are more robust to editing, showing less performance drop on general knowledge after editing. (3) Language model with large scale is more resistant to editing compared to small model. (4) The safety of the edited model, is significantly weakened, even for those safety-aligned models. Our findings indicate that current editing methods are only suitable for small-scale knowledge updates within language models, which motivates further research on more practical and reliable editing methods. The details of code and reproduction can be found in https://github.com/lqinfdim/EditingEvaluation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing

    cs.CL 2025-05 conditional novelty 6.0 of 10

    DecKER decouples reasoning from knowledge editing by planning with masked placeholders before retrieving edited facts, improving multi-hop QA accuracy after knowledge edits.

  2. AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation

    cs.CL 2025-05 conditional novelty 5.0 of 10

    AutoLaw's verifier-ranked legal-role jury with a similar-case demonstration beats majority voting for violation detection on three law and policy benchmarks.

Pith tools