Pith. sign in

REVIEW 3 cited by

Knowledge Editing on Black-box Large 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 2402.08631 v2 pith:MHEVKX3F submitted 2024-02-13 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords editingllmsblack-boxknowledgestylecurrentframeworkintroduce
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Knowledge editing (KE) aims to efficiently and precisely modify the behavior of large language models (LLMs) to update specific knowledge without negatively influencing other knowledge. Current research primarily focuses on white-box LLMs editing, overlooking an important scenario: black-box LLMs editing, where LLMs are accessed through interfaces and only textual output is available. In this paper, we first officially introduce KE on black-box LLMs and then propose a comprehensive evaluation framework to overcome the limitations of existing evaluations that are not applicable to black-box LLMs editing and lack comprehensiveness. To tackle privacy leaks of editing data and style over-editing in current methods, we introduce a novel postEdit framework, resolving privacy concerns through downstream post-processing and maintaining textual style consistency via fine-grained editing to original responses. Experiments and analysis on two benchmarks demonstrate that postEdit outperforms all baselines and achieves strong generalization, especially with huge improvements on style retention (average $+20.82\%\uparrow$).

Discussion (0). Continue with ORCID 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. DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients

    cs.CL 2025-05 reject novelty 6.0 of 10

    Combining knowledge retrieval, analogous patient case retrieval, and iterative textual-gradient refinement improves medical RAG accuracy across Chinese, English, and French benchmarks.

  2. IHEval: Evaluating Language Models on Following the Instruction Hierarchy

    cs.CL 2025-02 conditional novelty 6.0 of 10

    IHEval shows that current language models often follow lower-priority instructions over system messages, and simple prompting does not fix the problem.

  3. HiMat: DiT-based Ultra-High Resolution SVBRDF Generation

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    HiMat generates 4K, pixel-aligned SVBRDF material maps using a latent diffusion transformer with linear attention and a lightweight CrossStitch consistency module.

Pith tools