LLLie Li

Lie Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Lie Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Can GPT-4 provide human-level emotion support? Insights from machine learning-based evaluation framework

    by Wanghao Dong, Weijun Wang, Xinheng Han, Junhao Huang, Lie Li, Yinghui Huang


  • Open Access

    Human-AI Collaboration Enables GPT-4 to Achieve Human-Level User Feedback in Emotional Support Conversations: Integrative Modeling and Prompt Engineering Approaches (Preprint)

    by Yinghui Huang, Lie Li, Wanghao Dong, Yuhang Dong, Yingdan Huang, Hui Liu

    BACKGROUND Emotional support is crucial in enhancing social interactions, facilitating psychological interventions, and improving customer service outcomes by addressing individuals' emotional needs. The emergence of large language models (LLMs) offers potential for delivering emotional support on a large scale, but their effectiveness compared to human counselors has not been well understood. Evaluating and enhancing the emotional support capabilities of LLMs through targeted user-centered strategies is crucial for their successful real-world integration. OBJECTIVE This study aims to evaluate the emotional support capabilities of LLMs, specifically GPT-4o, and to introduce an integrative automatic evaluation framework focused on user perceived feedback (UPF). The framework seeks to enhance LLM performance in emotional support conversations (ESCs) by identifying psycholinguistic clues as intrinsic evaluation metrics and utilizing a customized Chain-of-Thought (CoT) prompting strategy. METHODS The study utilized a dataset of ESCs from human counselors to develop an explanatory predictive model using explainable artificial intelligence methods, following an integrative modeling paradigm rooted in computational social science. This model was designed to evaluate and interpret UPF scores for GPT-4o. Additionally, Hill's three-stage model of helping was integrated into a manually customized CoT prompting framework to evaluate GPT-4o's performance in ESCs. RESULTS GPT-4o achieved high UPF scores, demonstrating relative stability in performance, but it still significantly lags behind human counselors overall (Cliff's Delta = 0.087, P < 0.001). The evaluation framework identified 41 distinct linguistic clues related to emotional expression, social dynamics, cognitive processes, linguistic style, and decision-making stages, enhancing the understanding of both processes and outcomes in ESCs. Notably, GPT-4o's UPF scores significantly improved with the use of manually customized COT prompts (Cohen's d = 0.378, P < 0.001), showing no significant difference from the average performance of human counselors overall (Cliff's Delta = -0.014, P= 0.47). However, the COT prompts demonstrated a considerable advantage in specific emotion categories such as fear (Cliff's Delta = -0.23, P = 0.002), sadness (Cliff's Delta = -0.105, P = 0.012), and issues related to breakups with partners (Cliff's Delta = -0.06, P = 0.254). Compared to human counselors, GPT-4o is effective in reducing negative language and conveying emotional tone, but its overemphasis on emotional content weakens its causal reasoning, engagement prompting, and cognitive depth, limiting its ability to handle complex questions and scenarios. CONCLUSIONS This study offers preliminary evidence of GPT-4o's emotional support capabilities and introduces a UPF-centered integrative evaluation framework for ESCs. The findings suggest a cautiously optimistic outlook for applying advanced LLMs in emotional support services, though significant challenges persist, particularly in deepening conversational exploration and personalizing language. The proposed framework emphasizes the integration of human expertise into LLMs, enhancing their efficacy and contributing to developing trustworthy AI-based emotional support services.


  • Open Access

    Human-AI Collaboration Supporting GPT-4o Achieving Human-Level User Feedback in Emotional Support Conversations: Integrative Modeling and Prompt Engineering Approaches (Preprint)

    by Yinghui Huang, Lie Li, Wanghao Dong, Yuhang Dong, Yingdan Huang, Hui Liu

    BACKGROUND Emotional support plays a crucial role in enhancing social interactions, facilitating psychological interventions, and improving customer service outcomes by addressing individuals' emotional needs. The emergence of large language models (LLMs) holds promise for delivering emotional support on a large scale, but their effectiveness compared to human counselors is still not well understood. Evaluating and enhancing the emotional support capabilities of LLMs through targeted user-centered strategies is crucial for their successful real-world integration. OBJECTIVE This study aims to evaluate the emotional support capabilities of large language models (LLMs), specifically GPT-4o, and to introduce an integrative automatic evaluation framework centered on user-perceived feedback. The framework is designed to enhance LLM performance in emotional support conversations (ESCs) by identifying psycholinguistic clues as intrinsic evaluation metrics and leveraging a customized Chain-of-Thought (CoT) prompting framework. METHODS The study used a dataset of emotional support conversations from human counselors. An explanatory predictive model was developed using explainable artificial intelligence methods, following an integrative modeling paradigm rooted in computational social science. The model evaluated and interpreted user-perceived feedback scores for GPT-4o. Additionally, the study integrated Hill’s three-stage model of helping into a manually customized chain of thought prompting framework to systematically evaluate GPT-4o's performance in ESCs. RESULTS GPT-4o achieved high user-perceived feedback scores, demonstrating relative stability in its performance, but it still significantly trails behind human counselors overall (Cliff's Delta = 0.087, p < 0.001). The evaluation framework, which identified 41 distinct linguistic clues related to emotional expression, social dynamics, cognitive processes, linguistic style, and decision-making stages, enhanced the understanding of both processes and outcomes in ESCs. Notably, GPT-4o's user-perceived feedback scores significantly improved with the use of manually customized Chain of Thought prompts (p < 0.001, Cohen's d: 0.378), but showing no significant difference from the average performance of human counselors overall (p-adj: 0.47, Cliff's Delta: -0.014). However, thought prompts demonstrate a significant advantage in specific emotion categories such as fear (p: 0.002, Cliff's Delta: -0.23), sadness (p: 0.012, Cliff's Delta: -0.105), and break up with partner issues (p: 0.254, Cliff's Delta: -0.06). However, GPT-4o exhibited weaknesses in emotional understanding, cognitive complexity, language fluency, and handling extreme scenarios. CONCLUSIONS This study provides preliminary evidence of GPT-4o's emotional support capabilities and proposes a user-perceived feedback-centered integrative evaluation framework for ESCs. The findings suggest a cautiously optimistic outlook for the application of advanced large language models (LLMs) in emotional support services, although significant challenges remain, particularly in enhancing the depth of exploration in conversations and the personalization of language. The proposed framework encourages the integration of human expertise into LLMs, enhancing their efficacy and advancing the development of trustworthy AI-based emotional support services.

  • Open Access

    The Relationship between Environmental Information Disclosure and Financing Constraints: Evidence from Heavily Polluted Listed Companies in China

    by Xinman Li, Ruina Wang, Mingchen Wang, Shuang Xu, Lie Li

    With the acceleration of globalization and the vast awareness of the sustainable improvement approach by means of the worldwide community, environmental information disclosure (EID), as a sort of conversation bridge between businesses and stakeholders, is of brilliant magnitude to company financing. In order to discover the mechanism of EID on financing constraints, this paper makes use of balanced panel records of Chinese A-share closely polluting listed agencies from 2013-2022 to assemble a two-way fixed-effects model, and the effects exhibit that EID can alleviate company financing constraints. From an interior perspective, EID mitigates financing constraints by means of enhancing company savings ranking diagnosed by using stakeholders. From the exterior perspective, media attention have a nice moderating impact on the relationship between EID and financing constraints. The reliability of this paper is demonstrated through lagging variables and changing established variables. The consequences of heterogeneity evaluation exhibit that the inhibitory impact of EID on financing constraints is greater apparent when companies have greater fairness attention and weaker increase capacity. This paper gives theoretical help for businesses to make environmental facts disclosure, and presents recommendations for firms to enhance their financing techniques and the authorities to enhance the environmental records disclosure system.