Lexical density acts as an independent limiter on effective LLM context windows, with performance collapsing from near-perfect to below 60% as information density rises in controlled ~12k-token benchmarks.
Chain of knowledge: A framework for grounding large language mod- els with structured knowledge bases
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
DeSQ decomposes questions into atomic constraints, maps them to SPARQL fragments with placeholders, grounds the placeholders, and assembles complete queries, outperforming prior methods on four of five benchmarks.
EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming baselines on four datasets with linear indexing cost and zero token overhead.
A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
A survey classifying hallucination phenomena specific to large foundation models, establishing evaluation criteria, examining mitigation strategies, and discussing future directions.
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
citing papers explorer
-
Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs
Lexical density acts as an independent limiter on effective LLM context windows, with performance collapsing from near-perfect to below 60% as information density rises in controlled ~12k-token benchmarks.
-
DeSQ: Decomposition-based SPARQL Query Generation
DeSQ decomposes questions into atomic constraints, maps them to SPARQL fragments with placeholders, grounds the placeholders, and assembles complete queries, outperforming prior methods on four of five benchmarks.
-
EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval
EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming baselines on four datasets with linear indexing cost and zero token overhead.
-
Retrieval-Augmented Generation with Graphs (GraphRAG)
A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.
-
Retrieval-Augmented Generation for Large Language Models: A Survey
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
-
A Survey of Hallucination in Large Foundation Models
A survey classifying hallucination phenomena specific to large foundation models, establishing evaluation criteria, examining mitigation strategies, and discussing future directions.
-
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.