Pith. sign in

REVIEW 3 cited by

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

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 2403.07175 v3 pith:UUUJNUEQ submitted 2024-03-11 cs.CL cs.AI

Akshat Gupta , Sidharth Baskaran , Gopala Anumanchipalli This is my paper
classification cs.CLcs.AI
keywords modeleditsromeeditingdisablingcollapseimplementationsequential
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent work using Rank-One Model Editing (ROME), a popular model editing method, has shown that there are certain facts that the algorithm is unable to edit without breaking the model. Such edits have previously been called disabling edits. These disabling edits cause immediate model collapse and limits the use of ROME for sequential editing. In this paper, we show that disabling edits are an artifact of irregularities in the implementation of ROME. With this paper, we provide a more stable implementation ROME, which we call r-ROME and show that model collapse is no longer observed when making large scale sequential edits with r-ROME, while further improving generalization and locality of model editing compared to the original implementation of ROME. We also provide a detailed mathematical explanation of the reason behind disabling edits.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Efficient Knowledge Editing via Minimal Precomputation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Precomputing only a few thousand hidden vectors instead of 44 million is enough for MEMIT, ROME, and EMMET editing to match full-precomputation scores on CounterFact.

  2. Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations

    cs.AI 2025-06 conditional novelty 6.0 of 10

    SSP adds a learned, sample-specific noise prompt to an LLM input and scores hallucination by the cosine shift in intermediate representations, outperforming output-confidence baselines on QA benchmarks.

  3. LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models

    cs.CL 2025-05 reject novelty 4.0 of 10

    A block-localizing fine-tuning method for gender debiasing is presented, but its stated loss is inconsistent with its reported behavior and the evaluation tables contain duplicate rows.

Pith tools