A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Ryan Sze-Yin Chan, Federico Nanni, Tomas Lazauskas, et al.
This paper presents a retrieval-augmented reasoning system using a lean Qwen2.5-Instruct model fine-tuned with synthetic reasoning traces, achieving near-frontier performance on domain-specific queries while remaining locally deployable.
Hieu Tran, Zonghai Yao, Junda Wang, et al.
RARE enhances LLM reasoning accuracy and factual integrity by integrating retrieval-augmented actions into Monte Carlo Tree Search, enabling open-source models to rival GPT-4.
Saman Marandi, Yu-Shu Hu, Mohammad Modarres
This paper presents a framework for automated construction of Dynamic Master Logic models as knowledge graphs from technical documentation using retrieval-augmented large language models, validated on a nuclear reactor system.
Bajaj, Payal, Campos, Daniel, Craswell, Nick, et al.
This paper presents a dataset for the Advertisement in Retrieval-Augmented Generation task at Touché 2025, using segments from MS MARCO V2.1 and queries from Webis Generated Native Ads 2024.
Unknown
This paper introduces MM-PoisonRAG, a novel attack framework that disrupts multimodal retrieval-augmented generation systems through local and global knowledge poisoning.
Unknown
This paper introduces M^3KG-RAG, a multimodal RAG framework that leverages a knowledge graph to deliver query-relevant and answer-useful context for multi-hop multimodal question answering.
Unknown
This paper introduces Contextualized Graph RAG (Cg-RAG), a citation graph retrieval-augmented approach for research question answering that enhances LLMs with structured knowledge.
Unknown
Introduces retrieval-augmented generation (RAG), combining pre-trained parametric and non-parametric memory for knowledge-intensive NLP tasks.
Unknown
This paper provides a comprehensive analysis of when to use graphs in retrieval-augmented generation, offering a decision framework and empirical comparisons of GraphRAG versus vector RAG.
Unknown
RankRAG unifies context ranking with retrieval-augmented generation in LLMs by jointly fine-tuning a single model for both retrieval and answer generation, improving performance on knowledge-intensive tasks.
Unknown
This paper investigates whether small language models with retrieval-augmented generation can match or replace large language models in computer science education.
Chao Jin, Zili Zhang, Xuanlin Jiang, et al.
RAGCache reduces RAG latency by caching intermediate states in a knowledge tree across GPU/host memory and overlapping retrieval with generation via dynamic speculative pipelining.