Benchmarking and Rethinking Knowledge Editing for Large Language Models
This work addresses the problem of inconsistent evaluation in knowledge editing for LLMs, providing insights for researchers and practitioners, though it is incremental in benchmarking existing methods.
The study benchmarked knowledge editing methods for Large Language Models, revealing that parameter-based approaches perform poorly under realistic conditions, while a simple baseline method, Selective Contextual Reasoning, consistently outperformed them across all settings.
Knowledge editing aims to update the embedded knowledge within Large Language Models (LLMs). However, existing approaches, whether through parameter modification or external memory integration, often suffer from inconsistent evaluation objectives and experimental setups. To address this gap, we conduct a comprehensive benchmarking study. In addition to fact-level datasets, we introduce more complex event-based datasets and general-purpose datasets drawn from other tasks. Our evaluation covers both instruction-tuned and reasoning-oriented LLMs, under a realistic autoregressive inference setting rather than teacher-forced decoding. Beyond single-edit assessments, we also evaluate multi-edit scenarios to better reflect practical demands. We employ four evaluation dimensions, including portability, and compare all recent methods against a simple and straightforward baseline named Selective Contextual Reasoning (SCR). Empirical results reveal that parameter-based editing methods perform poorly under realistic conditions. In contrast, SCR consistently outperforms them across all settings. This study offers new insights into the limitations of current knowledge editing methods and highlights the potential of context-based reasoning as a more robust alternative.