We examine whether large language models (LLMs) can extract contextualized representation of Chinese public news articles to predict stock returns. Based on representativeness and influences, we consider seven LLMs: BERT, RoBERTa, FinBERT, Baichuan, ChatGLM, InternLM, and their ensemble model. We show that news tones and return forecasts extracted by LLMs from Chinese news significantly predict future returns. The value-weighted long-minus-short portfolios yield annualized returns between 35% and 67%, depending on the model. Building on the return predictive power of LLM signals, we further investigate its implications for information efficiency. The LLM signals contain firm fundamental information, and it takes two days for LLM signals to be incorporated into stock prices. The predictive power of the LLM signals is stronger for firms with more information frictions, more retail holdings and for more complex news. Interestingly, many investors trade in opposite directions of LLM signals upon news releases, and can benefit from the LLM signals. These findings suggest LLMs can be helpful in processing public news, and thus contribute to overall market efficiency.

This paper examines the role of earnings management in the underpricing and long-term performance of Chinese initial public offerings (IPOs) issued during the 1998-2003 period. It tests the earnings extrapolation hypothesis that naive investors extrapolate pre-issue earnings without fully adjusting for potential manipulation of accounting accruals, thereby inflating the initial trading price. If the hypothesis holds, underpricing will be positively related to initial earnings management. However, since the latter is subsequently corrected over time, it will lead to inferior long-term stock performance. The empirical evidence is consistent with both the earnings extrapolation and the long run underperformance hypotheses for our sample of 506 IPOs.

Based on prospect theory and individual investors’ biases such as representativeness heuristic and conservatism, we establish a behavioral model to explain the contrarian effect in China’s financial market. We find that contrarian effect is mainly attributed to trend chasing instead of disposition effect. Our model also suggests that small-cap stocks show stronger contrarian effect, phenomena confirmed by empirical research.