Pith. sign in

REVIEW 7 cited by

Transformer-Patcher: One Mistake worth One Neuron

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 2301.09785 v1 pith:Z6V4R52U submitted 2023-01-24 cs.CL cs.AI

Transformer-Patcher: One Mistake worth One Neuron

classification cs.CL cs.AI
keywords modeleditingmistakestransformer-patchermethodsmistaketimefixing
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Transformer-based Pretrained Language Models (PLMs) dominate almost all Natural Language Processing (NLP) tasks. Nevertheless, they still make mistakes from time to time. For a model deployed in an industrial environment, fixing these mistakes quickly and robustly is vital to improve user experiences. Previous works formalize such problems as Model Editing (ME) and mostly focus on fixing one mistake. However, the one-mistake-fixing scenario is not an accurate abstraction of the real-world challenge. In the deployment of AI services, there are ever-emerging mistakes, and the same mistake may recur if not corrected in time. Thus a preferable solution is to rectify the mistakes as soon as they appear nonstop. Therefore, we extend the existing ME into Sequential Model Editing (SME) to help develop more practical editing methods. Our study shows that most current ME methods could yield unsatisfying results in this scenario. We then introduce Transformer-Patcher, a novel model editor that can shift the behavior of transformer-based models by simply adding and training a few neurons in the last Feed-Forward Network layer. Experimental results on both classification and generation tasks show that Transformer-Patcher can successively correct up to thousands of errors (Reliability) and generalize to their equivalent inputs (Generality) while retaining the model's accuracy on irrelevant inputs (Locality). Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME). The code is available at https://github.com/ZeroYuHuang/Transformer-Patcher.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment

    cs.AI 2026-05 unverdicted novelty 7.0

    Introduces Latent Adversarial Robustification and Rank-Constrained Subspace Learning to enable robust generalization in multimodal knowledge editing through adversarial subspace alignment.

  2. Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models

    cs.CL 2026-05 unverdicted novelty 6.0

    LDKE framework localizes fact-specific layers and disentangles inputs to improve generalization and locality in multimodal knowledge editing for MLLMs.

  3. Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs'Hallucinations

    cs.CL 2026-05 conditional novelty 6.0

    EAACD reduces hallucination in MoE LLMs by contrasting predictions of high-reliability expert groups against hallucination-amplified low-reliability expert groups.

  4. The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

    cs.LG 2026-04 conditional novelty 6.0

    Knowledge conflicts in hypernetwork LLM adaptation stem from constant adapter margins losing to frequency-dependent pretrained margins; selective layer boosting and conflict-aware triggering raise deep-conflict accura...

  5. Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs

    cs.CL 2026-06 unverdicted novelty 5.0

    ORE decouples semantic entanglement in LLM hidden states via orthogonal edit vectors and a gated non-linear head, improving batch knowledge editing performance including cross-lingual cases.

  6. The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

    cs.LG 2026-04 unverdicted novelty 5.0

    Knowledge conflicts in hypernetwork LLM adaptation stem from constant adapter margins losing to frequency-dependent pretrained margins; selective layer boosting and conflict-aware triggering close the gap.

  7. Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression

    cs.AI 2026-04 unverdicted novelty 5.0

    LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing tr...