A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
SGD-KV compresses LLM KV caches via head-level budget allocation and token-level selection guided by summarization, building on SnapKV-style cumulative attention.
Xinze Li, Yixin Cao, Yubo Ma, et al.
This paper compares Long Context and RAG for LLMs, finding LC generally outperforms RAG on QA benchmarks, with summarization-based retrieval matching LC, and highlights context relevance as an overlooked factor.
Haopeng Zhang, Philip S. Yu, Jiawei Zhang
A comprehensive survey of text summarization covering statistical methods, deep learning, PLMs, and LLMs, including datasets, metrics, and future directions.
Jiangnan Fang, Cheng-Tse Liu, Jieun Kim, et al.
A multi-LLM framework for text summarization using centralized and decentralized evaluation strategies.
Unknown
Proposes TLDR, a method for extreme summarization of scientific papers into single-sentence summaries of key contributions.
Unknown
PEGASUS introduces a self-supervised pre-training objective that masks important sentences in documents and generates them as a summary, improving abstractive summarization.
Yubin Hong, Chaofan Li, Jingyi Zhang, et al.
FG-RAG introduces a context-aware fine-grained graph retrieval-augmented generation framework to improve query-focused summarization.
Darren Edge, Ha Trinh, Newman Cheng, et al.
This paper introduces Graph RAG, a method that uses knowledge graphs to improve query-focused summarization by enhancing comprehensiveness and diversity over naive RAG.