A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Fei Wang, Xingchen Wan, Ruoxi Sun, et al.
Astute RAG adaptively elicits internal knowledge from LLMs and iteratively consolidates it with external sources to overcome imperfect retrieval in RAG.
Adi Simhi, Jonathan Herzig, Idan Szpektor, et al.
This paper distinguishes between two types of LLM hallucinations—HK- (model lacks knowledge) and HK+ (model has knowledge but answers incorrectly)—and shows that distinguishing them improves mitigation.
Zhengren Wang, Jiayang Yu, Dongsheng Ma, et al.
RARE decouples knowledge storage from reasoning by externalizing domain knowledge to retrievable sources and internalizing reasoning patterns, enabling lightweight models to surpass GPT-4 and DeepSeek-R1 by ~20% accuracy.
Kaiwen Wei, Rui Shan, Dongsheng Zou, et al.
MIRAGE enhances test-time scaling for medical QA by combining multi-path parallel inference with structured knowledge graph retrieval to reduce error accumulation and improve traceability.
Jeremy Yang, Kathryn Zyskowski, Noah Yonack, et al.
AI agents autonomously execute knowledge work, reducing completion time by 87% and cost by 94% while expanding task scope and quality.
Craig Knox, Mike Wilson, Christen M. Klinger, et al.
DrugBank 6.0 expands the gold-standard drug knowledgebase with 72% more FDA-approved drugs, 300% more drug-drug interactions, and rich spectral data for small molecules.
Vikram S Chundawat, Ayush K Tarun, Murari Mandal, et al.
Introduces zero-shot machine unlearning, enabling data deletion from ML models without any original training samples, using error minimizing-maximizing noise and gated knowledge transfer.
Jakub Swacha, Michał Gracel
A survey of 47 papers on RAG chatbots in education, analyzing their character, target support, knowledge scope, LLM, and evaluation.
Nourhan Ibrahim, Samar AboulEla, Ahmed Ibrahim, et al.
This survey classifies LLM-KG integration into three paradigms—KG-augmented LLMs, LLM-augmented KGs, and synergized frameworks—and evaluates their methodologies, metrics, benchmarks, and challenges.
Paul C. D. Hawkins, A. Geoffrey Skillman, Gregory L. Warren, et al.
OMEGA is a systematic, knowledge-based conformer generator validated against high-quality PDB and CSD structures, showing strong performance in reproducing crystallographic conformations.
Freitas, Tiago Carvalho, Costa Neto, Alvaro, Pereira, Maria João Varanda, et al.
This paper outlines the potential role of LLMs in knowledge engineering, proposing hybrid neuro-symbolic systems and natural language knowledge engineering.
Yan Hu, Qingyu Chen, Jingcheng Du, et al.
This paper shows that task-specific prompt engineering, incorporating medical knowledge and few-shot examples, significantly improves GPT-3.5 and GPT-4 performance on clinical NER tasks, though still below BioClinicalBERT.