Tootfinder

What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge
Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Yuan He, Jiaoyan Chen, Evgeny Kharlamov, Steffen Staab
https://arxiv.org/abs/2508.08344

What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge
Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the structured evidence of knowledge graphs. However, current evaluation practices fall short: existing benchmarks often include questions that can be directly answered using existing triples in KG, making it unclear whether models perform reasoning or simply retrieve answers directly. Moreover, inconsistent evaluation metrics …

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
Stanley Ngugi
https://arxiv.org/abs/2508.07075

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
Large Language Models (LLMs) struggle with dynamic knowledge updates, especially when new information conflicts with deeply embedded facts. Such conflicting factual edits often lead to two critical issues: resistance to adopting the new fact and severe catastrophic forgetting of unrelated knowledge. This paper introduces and evaluates a novel "unlearn-then-learn" strategy for precise knowledge editing in LLMs, leveraging the parameter-efficient fine-tuning (PEFT) technique, Infused Adapter by I…

Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment
Tianyu Chen, Jian Lou, Wenjie Wang
https://arxiv.org/abs/2506.10030 https:/…

Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment
As Retrieval-Augmented Generation (RAG) evolves into service-oriented platforms (Rag-as-a-Service) with shared knowledge bases, protecting the copyright of contributed data becomes essential. Existing watermarking methods in RAG focus solely on textual knowledge, leaving image knowledge unprotected. In this work, we propose AQUA, the first watermark framework for image knowledge protection in Multimodal RAG systems. AQUA embeds semantic signals into synthetic images using two complementary meth…

WATCH: Aaron Rodgers refuses to sign for 'autograph hound' after testing his NFL game knowledge

https://www.cbssports.com/nfl/news/watch-a

"Ultimately, engaging the public enriches our scholarship. It pushes us to think more carefully about clarity, ethics, and relevance. It also ensures that the knowledge we produce contributes to a wider societal good, affirming the role of the university not just as a place of knowledge production, but also of public service."
#OpenScience
https://social.edu.nl/@Bibliothecaris/114833640819292319

Intersectoral Knowledge in AI and Urban Studies: A Framework for Transdisciplinary Research
Rashid Mushkani
https://arxiv.org/abs/2508.07507 https://arxiv.…

Intersectoral Knowledge in AI and Urban Studies: A Framework for Transdisciplinary Research
Transdisciplinary approaches are increasingly essential for addressing grand societal challenges, particularly in complex domains such as Artificial Intelligence (AI), urban planning, and social sciences. However, effectively validating and integrating knowledge across distinct epistemic and ontological perspectives poses significant difficulties. This article proposes a six-dimensional framework for assessing and strengthening transdisciplinary knowledge validity in AI and city studies, based …

Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
Vaibhav Chaudhary, Neha Soni, Narotam Singh, Amita Kapoor
https://arxiv.org/abs/2509.09272

Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
Knowledge graphs, a powerful tool for structuring information through relational triplets, have recently become the new front-runner in enhancing question-answering systems. While traditional Retrieval Augmented Generation (RAG) approaches are proficient in fact-based and local context-based extraction from concise texts, they encounter limitations when addressing the thematic and holistic understanding of complex, extensive texts, requiring a deeper analysis of both text and context. This pape…

When Is Prior Knowledge Helpful? Exploring the Evaluation and Selection of Unsupervised Pretext Tasks from a Neuro-Symbolic Perspective
Lin-Han Jia, Si-Yu Han, Wen-Chao Hu, Jie-Jing Shao, Wen-Da Wei, Zhi Zhou, Lan-Zhe Guo, Yu-Feng Li
https://arxiv.org/abs/2508.07299

When Is Prior Knowledge Helpful? Exploring the Evaluation and Selection of Unsupervised Pretext Tasks from a Neuro-Symbolic Perspective
Neuro-symbolic (Nesy) learning improves the target task performance of models by enabling them to satisfy knowledge, while semi/self-supervised learning (SSL) improves the target task performance by designing unsupervised pretext tasks for unlabeled data to make models satisfy corresponding assumptions. We extend the Nesy theory based on reliable knowledge to the scenario of unreliable knowledge (i.e., assumptions), thereby unifying the theoretical frameworks of SSL and Nesy. Through rigorous t…

Membership and Memorization in LLM Knowledge Distillation
Ziqi Zhang, Ali Shahin Shamsabadi, Hanxiao Lu, Yifeng Cai, Hamed Haddadi
https://arxiv.org/abs/2508.07054 https://

Membership and Memorization in LLM Knowledge Distillation
Recent advances in Knowledge Distillation (KD) aim to mitigate the high computational demands of Large Language Models (LLMs) by transferring knowledge from a large ''teacher'' to a smaller ''student'' model. However, students may inherit the teacher's privacy when the teacher is trained on private data. In this work, we systematically characterize and investigate membership and memorization privacy risks inherent in six LLM KD techniques. Using instruction-tuning settings that span seven NLP t…

CountTRuCoLa: Rule Confidence Learning for Temporal Knowledge Graph Forecasting
Julia Gastinger, Christian Meilicke, Heiner Stuckenschmidt
https://arxiv.org/abs/2509.09474 https…

CountTRuCoLa: Rule Confidence Learning for Temporal Knowledge Graph Forecasting
We address the task of temporal knowledge graph (TKG) forecasting by introducing a fully explainable method based on temporal rules. Motivated by recent work proposing a strong baseline using recurrent facts, our approach learns four simple types of rules with a confidence function that considers both recency and frequency. Evaluated on nine datasets, our method matches or surpasses the performance of eight state-of-the-art models and two baselines, while providing fully interpretable predictio…