pith. sign in

arxiv: 2402.08631 · v2 · pith:MHEVKX3Fnew · submitted 2024-02-13 · 💻 cs.CL · cs.AI· cs.LG

Knowledge Editing on Black-box Large Language Models

classification 💻 cs.CL cs.AIcs.LG
keywords editingllmsblack-boxknowledgestylecurrentframeworkintroduce
0
0 comments X
read the original 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 $+20.82\%\uparrow$).

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 2 Pith papers

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

  1. Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models

    cs.CL 2026-04 unverdicted novelty 7.0

    Supervised fine-tuning of LLMs often fails to fully internalize all training instances due to five recurring causes including missing prerequisites and data conflicts, as diagnosed via a new framework across multiple models.

  2. Exposing the Illusion of Erasure in Knowledge Editing for LLMs

    cs.LG 2026-06 unverdicted novelty 6.0

    Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.