GraphReader
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
proposes a graph-based agent system to enhance the long-context abilities of LLMs; it structures long text into a graph and employs an agent to explore the graph (using predefined functions guided by a step-by-step rational plan) to effectively generate answers for questions; consistently outperforms GPT-4-128k across context lengths from 16k to 256k.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack