Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces C-Unseen, a novel framework for detecting weak signals in Dynamic Temporal Knowledge Graphs (DTKGs) by leveraging large language model (LLM) reasoning. By defining weak signals as rare, semantically coherent subgraphs that emerge across consecutive snapshots, the framework employs a Rare Subgraphs Extractor to identify these subgraphs through chain-of-thought reasoning, and a Weak Signal Alerter to monitor their persistence over time. Experimental evaluations reveal that C-Unseen significantly outperforms traditional detection methods based on keyword frequency, topic modeling, and untyped graph topology.
C-Unseen reveals that LLMs can effectively identify weak signals in evolving knowledge graphs, outperforming conventional detection methods.
Weak signals are early, low-visibility indicators that precede significant changes before those changes become established. Existing detection methods, based on keyword frequency, topic modeling, or untyped graph topology, fail to capture the semantic and relational structure through which such signals manifest. In this paper, we propose C-Unseen, a self-interpretable framework for weak signal detection in Dynamic Temporal Knowledge Graphs (DTKGs). We define a weak signal as a rare, semantically coherent subgraph that proliferates across consecutive TKG snapshots. The framework operates through two modules: a Rare Subgraphs Extractor, in which an LLM identifies subgraphs whose content is in tension with the dominant snapshot narrative via chain-of-thought reasoning, and a Weak Signal Alerter, in which the persistence of these rare subgraphs is tracked across time steps to isolate true weak signals. Experimental results demonstrate that C-Unseen outperforms keyword-, topic-, and graph-based baselines.