Updating Language Models with Unstructured Facts: Towards Practical Knowledge Editing

• URL: http://arxiv.org/abs/2402.18909v1
• Date: Thu, 29 Feb 2024 07:08:34 GMT
• Title: Updating Language Models with Unstructured Facts: Towards Practical Knowledge Editing
• Authors: Xiaobao Wu, Liangming Pan, William Yang Wang, Anh Tuan Luu
• Abstract summary: We propose a new benchmark, Unstructured Knowledge Editing (UKE) UKE evaluates editing performance directly using unstructured texts as knowledge updates, termed unstructured facts. We conduct extensive experiments on newly built datasets and demonstrate that UKE poses a significant challenge to state-of-the-art knowledge editing methods.
• Score: 87.35944788684958
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge editing aims to inject knowledge updates into language models to keep them correct and up-to-date. However, its current evaluation strategies are notably impractical: they solely update with well-curated structured facts (triplets with subjects, relations, and objects), whereas real-world knowledge updates commonly emerge in unstructured texts like news articles. In this paper, we propose a new benchmark, Unstructured Knowledge Editing (UKE). It evaluates editing performance directly using unstructured texts as knowledge updates, termed unstructured facts. Hence UKE avoids the laborious construction of structured facts and enables efficient and responsive knowledge editing, becoming a more practical benchmark. We conduct extensive experiments on newly built datasets and demonstrate that UKE poses a significant challenge to state-of-the-art knowledge editing methods, resulting in their critical performance declines. We further show that this challenge persists even if we extract triplets as structured facts. Our analysis discloses key insights to motivate future research in UKE for more practical knowledge editing.

Related papers

• Event-level Knowledge Editing [53.767465515537545]
  Existing work edits large language models (LLMs) at the level of factual knowledge triplets. We propose a new task setting: event-level knowledge editing, which directly edits new events into LLMs. We construct a high-quality event-level editing benchmark ELKEN, consisting of 1,515 event edits, 6,449 questions about factual knowledge, and 10,150 questions about future tendencies.
  arXiv  Detail & Related papers  (2024-02-20T15:36:41Z)
• Stable Knowledge Editing in Large Language Models [68.98582618305679]
  We introduce StableKE, a knowledge editing method based on knowledge augmentation rather than knowledge localization. To overcome the expense of human labeling, StableKE integrates two automated knowledge augmentation strategies. StableKE surpasses other knowledge editing methods, demonstrating stability both edited knowledge and multi-hop knowledge.
  arXiv  Detail & Related papers  (2024-02-20T14:36:23Z)
• A Comprehensive Study of Knowledge Editing for Large Language Models [82.65729336401027]
  Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. This paper defines the knowledge editing problem and provides a comprehensive review of cutting-edge approaches. We introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches.
  arXiv  Detail & Related papers  (2024-01-02T16:54:58Z)
• History Matters: Temporal Knowledge Editing in Large Language Model [42.74144542674756]
  We introduce the task of Temporal Knowledge Editing (TKE) and establish a benchmark AToKe to evaluate current model editing methods. We find that while existing model editing methods are effective at making models remember new knowledge, the edited model catastrophically forgets historical knowledge. To address this gap, we propose a simple and general framework termed Multi-Editing with Time Objective (METO) for enhancing existing editing models.
  arXiv  Detail & Related papers  (2023-12-09T07:51:56Z)
• Assessing Knowledge Editing in Language Models via Relation Perspective [21.64869056276927]
  This paper constructs a new benchmark named RaKE, which focuses on relation-based knowledge editing. We establish a suite of innovative metrics for evaluation and conduct comprehensive experiments involving various knowledge editing baselines. Our research results confirm that knowledge related to relations is not only stored in the FFN network but also in the attention layers.
  arXiv  Detail & Related papers  (2023-11-15T15:44:42Z)
• Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators [78.63553017938911]
  Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks. However, community concerns abound regarding the factuality and potential implications of using this uncensored knowledge. We introduce CONNER, designed to evaluate generated knowledge from six important perspectives.
  arXiv  Detail & Related papers  (2023-10-11T08:22:37Z)
• Eva-KELLM: A New Benchmark for Evaluating Knowledge Editing of LLMs [54.22416829200613]
  Eva-KELLM is a new benchmark for evaluating knowledge editing of large language models. Experimental results indicate that the current methods for knowledge editing using raw documents are not effective in yielding satisfactory results.
  arXiv  Detail & Related papers  (2023-08-19T09:17:19Z)

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.