Pith. sign in

REVIEW 5 cited by

Tool Unlearning for Tool-Augmented LLMs

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 2502.01083 v2 pith:G3M4JCWQ submitted 2025-02-03 cs.LG cs.AIcs.CL

Jiali Cheng , Hadi Amiri This is my paper
classification cs.LGcs.AIcs.CL
keywords llmsunlearningtooltool-augmentedtoolsknowledgeabilitychallenges
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Tool-augmented large language models (LLMs) are often trained on datasets of query-response pairs, which embed the ability to use tools or APIs directly into the parametric knowledge of LLMs. Tool-augmented LLMs need the ability to forget learned tools due to security vulnerabilities, privacy regulations, or tool deprecations. However, ``tool unlearning'' has not been investigated in unlearning literature. We introduce this novel task, which requires addressing distinct challenges compared to traditional unlearning: knowledge removal rather than forgetting individual samples, the high cost of optimizing LLMs, and the need for principled evaluation metrics. To bridge these gaps, we propose ToolDelete, the first approach for unlearning tools from tool-augmented LLMs. It implements three key properties to address the above challenges for effective tool unlearning and introduces a new membership inference attack (MIA) model for effective evaluation. Extensive experiments on multiple tool learning datasets and tool-augmented LLMs show that ToolDelete effectively unlearns randomly selected tools, while preserving the LLM's knowledge on non-deleted tools and maintaining performance on general tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. CURE:Circuit-Aware Unlearning for LLM-based Recommendation

    cs.IR 2026-04 unverdicted novelty 7.0 of 10

    CURE disentangles LLM recommendation circuits into forget-specific, retain-specific, and task-shared modules with tailored update rules to achieve more effective unlearning than weighted baselines.

  2. Understanding Machine Unlearning Through the Lens of Mode Connectivity

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Unlearned models often lie in connected low-loss basins, and that geometry can predict unlearning difficulty and improve robustness to relearning attacks.

  3. Understanding Machine Unlearning Through the Lens of Mode Connectivity

    cs.LG 2026-07 unverdicted novelty 6.0 of 10

    Unlearned models usually connect to their originals by smooth low-loss paths, and the smoothness of that path can predict how hard the unlearning task was.

  4. A Numerical PDEs Approach to Evolution Equations in Shape Analysis Based on Regularized Morphoelasticity

    math.NA 2026-04 unverdicted novelty 4.0 of 10

    Regularized morphoelasticity yields a high-order elliptic system for continuous shape evolution that is solved by mixed finite elements in FEniCSx within an LDDMM-style optimal-control growth model.

  5. A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A survey and framework that categorizes generative model unlearning by point-wise versus concept-wise objectives, parameter-based versus non-parametric methods, and completeness/utility/efficiency evaluation.

Pith tools