CaseEdit: Enhancing Localized Commonsense Reasoning via Null-Space Constrained Knowledge Editing in Small Parameter Language Models
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Large language models (LLMs) exhibit strong performance on factual recall and general reasoning but struggle to adapt to user-specific, commonsense knowledge, a challenge particularly acute in small-parameter settings where computational efficiency is prioritized. We introduce CaseEdit, a new dataset and generation pipeline for evaluating localized, personalized commonsense knowledge editing in small LLMs to address this. Built upon the ATOMIC20/20 commonsense graph, CaseEdit uses a multi-stage inference process to generate both typical and atypical contextual edits for household objects, paired with targeted evaluation questions across four axes: reliability, generalization, locality, and portability. We evaluate established knowledge editing methods using CaseEdit and demonstrate that AlphaEdit, a technique employing null-space projection to minimize interference with unrelated knowledge, consistently outperforms other methods when applied to an LLaMA 3.2 3B model, even in scalability tests, showing minimal ripple effects. Our results indicate that using CaseEdit with effective editing techniques like AlphaEdit allows small models to internalize high-quality, context-sensitive common-sense knowledge, paving the way for lightweight, personalized assistants.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 17 of its 27 references that are in the map. First posted on arXiv 26 May 2025.
Builds on
17 of 27 references.
Closest ancestors · 1
Same direction, newest first
- 2024Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning25 Apr
Other references · 16
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2024GPT-4o System Cardcited by 4,588
- 2022Locating and Editing Factual Associations in GPTcited by 2,691
- 2022Mass-Editing Memory in a Transformercited by 1,001
- 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
- 2021Fast Model Editing at Scalecited by 498
- 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 372
- 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
- 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 236
4 more
- 2023Knowledge Editing for Large Language Models: A Surveycited by 194
- 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 163
- 2023EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Modelscited by 98
- 2024WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Modelscited by 92
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning
- 2025Benchmarking and Rethinking Knowledge Editing for Large Language Models
- 2025Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning
- 2024MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
- 2026CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models
- 2025ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering
- 2025HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning
- 2024From Data to Commonsense Reasoning: The Use of Large Language Models for Explainable AI