Tag
Hyper-Extract is an Apache 2.0 open-source tool that converts unstructured documents into structured knowledge bases, supporting knowledge graphs, time-series data, and spatial information, enabling high-accuracy AI queries.
Proposes InKH, an interaction-native knowledge harness architecture for financial LLM agents that absorbs user complexity through structured knowledge management and temporal memory, achieving significant improvements in latency, token cost, and stale-knowledge reduction.
This paper investigates the mechanisms underlying sequential knowledge editing in LLMs, showing that many regularization strategies are unnecessary and that stability emerges naturally from properly accounting for accumulated editing constraints.
This paper presents a mechanistic analysis of why LLMs hallucinate when reasoning over linearized structured knowledge, finding that hallucinations stem from systematic internal dynamics such as attention on shortcut cues and failures in semantic grounding in feed-forward layers, rather than random noise.