This study applies large language models (LLMs) to measure technological links and examines its predictive power in the Chinese stock market. Using the BAAI General Embedding (BGE) model, we extract semantic information from patent textual data to construct the technological momentum measure. As a comparison, the measure based on traditional International Patent Classification (IPC) is also considered. Empirical analysis shows that both measures significantly predict stock returns and they capture complementary dimensions of technological links. Further investigation through stratified analysis reveals the critical role of investor inattention in explaining their differential performance: in stocks with low investor inattention, IPC-based measure loses its predictive power while BGE-based measure remains significant, indicating that straightforward information is fully priced in while complex semantic relationships require greater cognitive processing; in stocks with high investor inattention, both measures exhibit predictability, with BGE-based measure showing stronger effects. These findings support behavioral finance theories suggesting that complex information diffuses more slowly in markets, especially under significant cognitive constraints, and demonstrate LLMs’ advantage in uncovering subtle technological connections that traditional methods overlook.

We conduct a comprehensive study on momentum spillovers in the Chinese stock market using varioustypes of economic linkages. We find that the news co-mention momentum spillover is signiffcantly strongercompared to other forms of momentum spillovers. Using spanning tests and Fama-MacBeth regressions,we further show that the news co-mention momentum spillover uniffes all different forms of momentum spillover effects in the Chinese stock market. Notably, the analyst co-coverage momentum spillover effect, which is the dominant species in the US stock market, is subsumed by the news co-mention momentum spillover effect in the Chinese stock market. We further explore the differences in the information content of links implied by news co-mentioning and other proxies. We suggest that the dominance of news co-mention momentum spillover over others can be attributed to two primary factors: comprehensive information and prompt updates.