StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models

• URL: http://arxiv.org/abs/2409.10132v1
• Date: Mon, 16 Sep 2024 09:48:56 GMT
• Title: StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models
• Authors: Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Hongcheng Gao, Junfeng Fang, Xueqi Cheng,
• Abstract summary: StruEdit consistently delivers the highest accuracy with lowest latency compared with other knowledge editing methods. Results show that StruEdit consistently delivers the highest accuracy with lowest latency compared with other knowledge editing methods.
• Score: 41.45831411548188
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As the modern tool of choice for question answering, large language models (LLMs) are expected to deliver answers with up-to-date knowledge. To achieve such ideal question-answering systems, locating and then editing outdated knowledge in the natural language outputs is a general target of popular knowledge editing methods. However, this target is challenging, as both identifying which tokens to edit in the reasoning steps and ensuring the coherence of the revised reasoning chain are difficult tasks. We argue that these challenges stem from the unstructured nature of natural language outputs. To address the above challenges, we propose $\textbf{Stru}$ctural $\textbf{Edit}$ing ($\textbf{StruEdit}$), an improved baseline for knowledge editing. We first prompt LLMs to produce structured outputs consisting of reasoning triplets. Then, StruEdit removes any potentially outdated knowledge and efficiently refills the structured outputs with up-to-date information in a single step. Experimental results show that StruEdit consistently delivers the highest accuracy with lowest latency compared with other knowledge editing methods.

Related papers

• Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models [65.10456412127405]
  A significant portion of real-world knowledge is stored in an unstructured format. Techniques like local layer key-value storage and term-driven optimization are not effective for handling unstructured knowledge. We propose a novel Unstructured Knowledge Editing method, namely UnKE, which extends previous assumptions in the layer dimension and token dimension.
  arXiv  Detail & Related papers  (2024-05-24T08:42:40Z)
• Detecting Edited Knowledge in Language Models [5.260519479124422]
  Knowledge editing methods (KEs) can update language models' obsolete or inaccurate knowledge learned from pre-training. Knowing whether a generated output is based on edited knowledge or first-hand knowledge from pre-training can increase users' trust in generative models. We propose a novel task: detecting edited knowledge in language models.
  arXiv  Detail & Related papers  (2024-05-04T22:02:24Z)
• EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries [69.72012539060731]
  We introduce a theoretical framework for efficient knowledge editing (KE) in large language models (LLMs) We propose a novel task of event-based knowledge editing that pairs facts with event descriptions. We empirically demonstrate the superiority of event-based editing over the existing setting on resolving uncertainty in edited models.
  arXiv  Detail & Related papers  (2024-02-17T16:34:50Z)
• On the Robustness of Editing Large Language Models [57.477943944826904]
  Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. This work seeks to understand the strengths and limitations of editing methods, facilitating practical applications of communicative AI.
  arXiv  Detail & Related papers  (2024-02-08T17:06:45Z)
• SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering [17.20346072074533]
  Recent model editing is a promising technique for efficiently updating a small amount of knowledge of large language models (LLMs) We propose a detachable and expandable Subject Word Embedding Altering (SWEA) framework, which finds the editing embeddings through token-level matching. We demonstrate the overall state-of-the-art (SOTA) performance of SWEA$oplus$OS on the textscCounterFact and zsRE datasets.
  arXiv  Detail & Related papers  (2024-01-31T13:08:45Z)
• DUnE: Dataset for Unified Editing [3.7346004746366384]
  We introduce DUnE-an editing benchmark where edits are natural language sentences. We show that retrieval-augmented language modeling can outperform specialized editing techniques.
  arXiv  Detail & Related papers  (2023-11-27T18:56:14Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• WikiIns: A High-Quality Dataset for Controlled Text Editing by Natural Language Instruction [56.196512595940334]
  We build and release WikiIns, a high-quality controlled text editing dataset with improved informativeness. With the high-quality annotated dataset, we propose automatic approaches to generate a large-scale silver'' training set.
  arXiv  Detail & Related papers  (2023-10-08T04:46:39Z)
• XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates [7.660511135287692]
  This paper introduces XATU, the first benchmark specifically designed for fine-grained instruction-based explainable text editing. XATU considers finer-grained text editing tasks of varying difficulty, incorporating lexical, syntactic, semantic, and knowledge-intensive edit aspects. We demonstrate the effectiveness of instruction tuning and the impact of underlying architecture across various editing tasks.
  arXiv  Detail & Related papers  (2023-09-20T04:58:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.