Pith. sign in

REVIEW 10 cited by

Modifying Memories in Transformer 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 2012.00363 v1 pith:PFHIOHXL submitted 2020-12-01 cs.CL cs.LG

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

Large Transformer models have achieved impressive performance in many natural language tasks. In particular, Transformer based language models have been shown to have great capabilities in encoding factual knowledge in their vast amount of parameters. While the tasks of improving the memorization and generalization of Transformers have been widely studied, it is not well known how to make transformers forget specific old facts and memorize new ones. In this paper, we propose a new task of \emph{explicitly modifying specific factual knowledge in Transformer models while ensuring the model performance does not degrade on the unmodified facts}. This task is useful in many scenarios, such as updating stale knowledge, protecting privacy, and eliminating unintended biases stored in the models. We benchmarked several approaches that provide natural baseline performances on this task. This leads to the discovery of key components of a Transformer model that are especially effective for knowledge modifications. The work also provides insights into the role that different training phases (such as pretraining and fine-tuning) play towards memorization and knowledge modification.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Online value-gradient normalization in lifelong LLM editing produces bounded, asymptotically orthogonal parameter updates; an explicit warm-up and full whitening (StableEdit) strengthen this effect and improve long-ho...

  2. Can Gradient Descent Simulate Prompting?

    cs.CL 2025-06 conditional novelty 7.0 of 10

    A MAML-style meta-training objective makes a single gradient step on new text recover part of the performance that prompting achieves, on reversal-curse and passage-QA tasks.

  3. Don't Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations

    cs.SE 2025-11 conditional novelty 6.0 of 10

    AdaLoRA-L restricts edits to API-specific layers and raises specificity by 33–836% (relative) on a new 3,000+ instance benchmark while staying close to AdaLoRA's effectiveness.

  4. Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

    cs.AI 2025-11 unverdicted novelty 6.0 of 10

    RILKE learns low-dimensional, paraphrase-robust modules in LLM representation space that enable interference-free lifelong knowledge edits while preserving base model utility.

  5. Potemkin Understanding in Large Language Models

    cs.CL 2025-06 conditional novelty 6.0 of 10

    LLMs frequently pass definition questions yet fail to use the same concepts in classification, generation, and editing tasks, a gap the authors call potemkin understanding.

  6. Is Fine-Tuning an Effective Solution? Reassessing Knowledge Editing for Unstructured Data

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A properly configured fine-tuning baseline outperforms specialized knowledge editing methods on unstructured knowledge editing, and stays ahead as batch size grows.

  7. ScEdit: Script-based Assessment of Knowledge Editing

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A script-based benchmark reveals that knowledge-editing methods perform far worse on 'How' style procedural questions than on the fact-recall questions used in standard evaluations.

  8. REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing

    cs.AI 2025-05 conditional novelty 6.0 of 10

    REACT edits LLM facts by adding a learned belief-shift vector to hidden states only when a classifier decides the context is edit-relevant, reducing overfitting on EVOKE while keeping balanced editing metrics.

  9. Break Through the Compression Bottleneck: From Theory to Practice

    cs.CL 2026-05 reject novelty 5.0 of 10

    The paper asserts a first proof that low-rank decomposition and quantization are non-orthogonal tools for LLM compression, recommends low-rank-first ordering, and adds a diagonal scaling fix (DAM) that reduces the com...

  10. Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA

    cs.CL 2025-09 conditional novelty 5.0 of 10

    Teaching an LLM to emit a fixed four-stage reasoning chain during fine-tuning makes single-pass multi-hop knowledge editing robust to distractor facts.

Pith tools