Lin Chen
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
Lin Chen has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Yong Li
Tsinghua University
8 shared publications - Fengli Xu
Tsinghua University
5 shared publications - James Evans
University of Chicago
4 shared publications - Pan Hui
Hong Kong University of Science and Technology (Guangzhou)
3 shared publications - Qianyue Hao
Tsinghua University
3 shared publications - Zhenyu Han
Department of Electronic Engineering, Tsinghua University, Beijing, China
3 shared publications
Latest Publications
- 26 October 2026
- Published by Springer Nature in Nature Human Behaviour
- p. 1-17
Large language models for computational social science
- 26 October 2026
- Published by Springer Nature in Nature Human Behaviour
- p. 1-17
Large language models for computational social science
- Open Access
- 29 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (16) , 1-35
Reinforcement Learning in the Era of Large Language Models: Challenges and Opportunities
Reinforcement learning (RL), is becoming essential in the post-training of large language models (LLMs), enhancing their capabilities and alignment with human preferences. However, adapting conventional RL to LLMs introduces challenges stemming from their massive parameter size and the vast natural language action space. In this survey, we conduct a systematic literature review on how RL are adapted and scaled as a fundamental post-training tools. First, we provide a taxonomy of challenges faced in each stage of the RL training loop, including action exploration, trajectory collection, reward evaluation, and model update. We then introduce recently developed methods to address these issues, ranging from logical structure navigation, training data curation to reward design and advantage estimation. Afterward, we elaborate on the application of these techniques in diverse domains such as mathematics, coding, medicine, and information retrieval, analyzing how innovations in the RL pipeline enhance the domain-specific LLMs. Finally, we discuss the limitations and side effects of applying RL to LLMs and explore open problems and future directions like the balance between efficiency and effectiveness, and algorithm-system co-design. This survey helps researchers understand recent progress and inspire novel research to address current challenges and realize the full potential of RL for LLMs.
- 29 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (16) , 1-35
Open AccessReinforcement Learning in the Era of Large Language Models: Challenges and Opportunities
Reinforcement learning (RL), is becoming essential in the post-training of large language models (LLMs), enhancing their capabilities and alignment with human preferences. However, adapting conventional RL to LLMs introduces challenges stemming from their massive parameter size and the vast natural language action space. In this survey, we conduct a systematic literature review on how RL are adapted and scaled as a fundamental post-training tools. First, we provide a taxonomy of challenges faced in each stage of the RL training loop, including action exploration, trajectory collection, reward evaluation, and model update. We then introduce recently developed methods to address these issues, ranging from logical structure navigation, training data curation to reward design and advantage estimation. Afterward, we elaborate on the application of these techniques in diverse domains such as mathematics, coding, medicine, and information retrieval, analyzing how innovations in the RL pipeline enhance the domain-specific LLMs. Finally, we discuss the limitations and side effects of applying RL to LLMs and explore open problems and future directions like the balance between efficiency and effectiveness, and algorithm-system co-design. This survey helps researchers understand recent progress and inspire novel research to address current challenges and realize the full potential of RL for LLMs.
- Top Cited Papers
- 17 February 2025
- Published by Springer Nature in Nature Human Behaviour
- Vol. 9 (4) , 654-664
Using human mobility data to quantify experienced urban inequalities
The lived experience of urban life is shaped by personal mobility through dynamic relationships and resources, marked not only by access and opportunity, but also inequality and segregation. The recent availability of fine-grained mobility data and context attributes ranging from venue type to demographic mixture offer researchers a deeper understanding of experienced inequalities at scale, and pose many new questions. Here we review emerging uses of urban mobility behaviour data, and propose an analytic framework to represent mobility patterns as a temporal bipartite network between people and places. As this network reconfigures over time, analysts can track experienced inequality along three critical dimensions: social mixing with others from specific demographic backgrounds, access to different types of facilities, and spontaneous adaptation to unexpected events, such as epidemics, conflicts or disasters. This framework traces the dynamic, lived experiences of urban inequality and complements prior work on static inequalities experience at home and work.
- 17 February 2025
- Published by Springer Nature in Nature Human Behaviour
- Vol. 9 (4) , 654-664
Top Cited PapersUsing human mobility data to quantify experienced urban inequalities
The lived experience of urban life is shaped by personal mobility through dynamic relationships and resources, marked not only by access and opportunity, but also inequality and segregation. The recent availability of fine-grained mobility data and context attributes ranging from venue type to demographic mixture offer researchers a deeper understanding of experienced inequalities at scale, and pose many new questions. Here we review emerging uses of urban mobility behaviour data, and propose an analytic framework to represent mobility patterns as a temporal bipartite network between people and places. As this network reconfigures over time, analysts can track experienced inequality along three critical dimensions: social mixing with others from specific demographic backgrounds, access to different types of facilities, and spontaneous adaptation to unexpected events, such as epidemics, conflicts or disasters. This framework traces the dynamic, lived experiences of urban inequality and complements prior work on static inequalities experience at home and work.
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 307-318
Large Language Model-driven Meta-structure Discovery in Heterogeneous Information Network
Heterogeneous information networks (HIN) have gained increasing popularity in recent years for capturing complex relations between diverse types of nodes. Meta-structures are proposed as a useful tool to identify the important patterns in HINs, but hand-crafted meta-structures pose significant challenges for scaling up, drawing wide research attention towards developing automatic search algorithms. Previous efforts primarily focused on searching for meta-structures with good empirical performance, overlooking the importance of human comprehensibility and generalizability. To address this challenge, we draw inspiration from the emergent reasoning abilities of large language models (LLMs). We propose ReStruct, a meta-structure search framework that integrates LLM reasoning into the evolutionary procedure. ReStruct uses a grammar translator to encode the meta-structures into natural language sentences, and leverages the reasoning power of LLMs to evaluate their semantic feasibility. Besides, ReStruct also employs performance-oriented evolutionary operations. These two competing forces allow ReStruct to jointly optimize the semantic explainability and empirical performance of meta-structures. Furthermore, ReStruct contains a differential LLM explainer to generate and refine natural language explanations for the discovered meta-structures by reasoning through the search history. Experiments on eight representative HIN datasets demonstrate that ReStruct achieves state-of-the-art performance in both recommendation and node classification tasks. Moreover, a survey study involving 73 graduate students shows that the discovered meta-structures and generated explanations by ReStruct are substantially more comprehensible. Our code and questionnaire are available at https://github.com/LinChen-65/ReStruct.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 307-318
Open AccessLarge Language Model-driven Meta-structure Discovery in Heterogeneous Information Network
Heterogeneous information networks (HIN) have gained increasing popularity in recent years for capturing complex relations between diverse types of nodes. Meta-structures are proposed as a useful tool to identify the important patterns in HINs, but hand-crafted meta-structures pose significant challenges for scaling up, drawing wide research attention towards developing automatic search algorithms. Previous efforts primarily focused on searching for meta-structures with good empirical performance, overlooking the importance of human comprehensibility and generalizability. To address this challenge, we draw inspiration from the emergent reasoning abilities of large language models (LLMs). We propose ReStruct, a meta-structure search framework that integrates LLM reasoning into the evolutionary procedure. ReStruct uses a grammar translator to encode the meta-structures into natural language sentences, and leverages the reasoning power of LLMs to evaluate their semantic feasibility. Besides, ReStruct also employs performance-oriented evolutionary operations. These two competing forces allow ReStruct to jointly optimize the semantic explainability and empirical performance of meta-structures. Furthermore, ReStruct contains a differential LLM explainer to generate and refine natural language explanations for the discovered meta-structures by reasoning through the search history. Experiments on eight representative HIN datasets demonstrate that ReStruct achieves state-of-the-art performance in both recommendation and node classification tasks. Moreover, a survey study involving 73 graduate students shows that the discovered meta-structures and generated explanations by ReStruct are substantially more comprehensible. Our code and questionnaire are available at https://github.com/LinChen-65/ReStruct.
- Open Access
- 9 January 2024
- Published by Springer Nature in Humanities and Social Sciences Communications
- Vol. 11 (1) , 1-12
Counterfactual mobility network embedding reveals prevalent accessibility gaps in U.S. cities
Living in cities affords expanded access to various resources, infrastructures, and services at reduced travel costs, which improves social life and promotes systemic gains. However, recent research shows that urban dwellers also experience inequality in accessing urban facilities, which manifests in distinct travel and visitation patterns for residents with different demographic backgrounds. Here, we go beyond simple flawed correlation analysis and reveal prevalent accessibility gaps by quantifying the causal effects of resident demographics on mobility patterns extracted from U.S. residents’ detailed interactions with millions of urban venues. Moreover, to efficiently reveal micro neighborhood-level accessibility gaps, we design a novel Counterfactual RANdom-walks-based Embedding (CRANE) method to learn continuous embedding vectors on urban mobility networks with confounding effects disentangled. Our analysis reveals significant income and racial gaps in mobility frequency and visitation rates to sports and education venues. Besides, bachelor’s degree holders experience greater mobility reduction during the COVID-19 crisis. With extensive experiments on neighborhood-level accessibility prediction and visualizing accessibility gaps with embeddings vectors, we demonstrate that the counterfactual mobility network embeddings can improve the explanatory capacity and robustness of revealed accessibility gaps by extending them from aggregate statistics to individual neighborhoods and allowing for cross-city knowledge transfer. As such, urban mobility networks can reveal consistent accessibility gaps in the U.S., calling for urgent urban design policies to fill in the gaps.
- 9 January 2024
- Published by Springer Nature in Humanities and Social Sciences Communications
- Vol. 11 (1) , 1-12
Open AccessCounterfactual mobility network embedding reveals prevalent accessibility gaps in U.S. cities
Living in cities affords expanded access to various resources, infrastructures, and services at reduced travel costs, which improves social life and promotes systemic gains. However, recent research shows that urban dwellers also experience inequality in accessing urban facilities, which manifests in distinct travel and visitation patterns for residents with different demographic backgrounds. Here, we go beyond simple flawed correlation analysis and reveal prevalent accessibility gaps by quantifying the causal effects of resident demographics on mobility patterns extracted from U.S. residents’ detailed interactions with millions of urban venues. Moreover, to efficiently reveal micro neighborhood-level accessibility gaps, we design a novel Counterfactual RANdom-walks-based Embedding (CRANE) method to learn continuous embedding vectors on urban mobility networks with confounding effects disentangled. Our analysis reveals significant income and racial gaps in mobility frequency and visitation rates to sports and education venues. Besides, bachelor’s degree holders experience greater mobility reduction during the COVID-19 crisis. With extensive experiments on neighborhood-level accessibility prediction and visualizing accessibility gaps with embeddings vectors, we demonstrate that the counterfactual mobility network embeddings can improve the explanatory capacity and robustness of revealed accessibility gaps by extending them from aggregate statistics to individual neighborhoods and allowing for cross-city knowledge transfer. As such, urban mobility networks can reveal consistent accessibility gaps in the U.S., calling for urgent urban design policies to fill in the gaps.
- Open Access
- 20 December 2023
- Published by International Society of Global Health in Journal of Global Health
- Vol. 13, 06038
How enlightened self-interest guided global vaccine sharing benefits all: A modeling study
Vaccines are a key resource for curbing the global spread of infectious diseases [1] through effective epidemic control at a relatively low economic cost compared with lockdowns or quarantine measures. The scarcity of vaccine resources during the early stage of disease outbreaks makes them a highly-demanded resource hoarded by high-income countries under the influence of […]
- 20 December 2023
- Published by International Society of Global Health in Journal of Global Health
- Vol. 13, 06038
Open AccessHow enlightened self-interest guided global vaccine sharing benefits all: A modeling study
Vaccines are a key resource for curbing the global spread of infectious diseases [1] through effective epidemic control at a relatively low economic cost compared with lockdowns or quarantine measures. The scarcity of vaccine resources during the early stage of disease outbreaks makes them a highly-demanded resource hoarded by high-income countries under the influence of […]
- Open Access
- 9 November 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 14 (1) , 1-27
Hierarchical Multi-agent Model for Reinforced Medical Resource Allocation with Imperfect Information
With the advent of the COVID-19 pandemic, the shortage in medical resources became increasingly more evident. Therefore, efficient strategies for medical resource allocation are urgently needed. However, conventional rule-based methods employed by public health experts have limited capability in dealing with the complex and dynamic pandemic-spreading situation. In addition, model-based optimization methods such as dynamic programming (DP) fail to work since we cannot obtain a precise model in real-world situations most of the time. Model-free reinforcement learning (RL) is a powerful tool for decision-making; however, three key challenges exist in solving this problem via RL: (1) complex situations and countless choices for decision-making in the real world; (2) imperfect information due to the latency of pandemic spreading; and (3) limitations on conducting experiments in the real world since we cannot set up pandemic outbreaks arbitrarily. In this article, we propose a hierarchical RL framework with several specially designed components. We design a decomposed action space with a corresponding training algorithm to deal with the countless choices, ensuring efficient and real-time strategies. We design a recurrent neural network–based framework to utilize the imperfect information obtained from the environment. We also design a multi-agent voting method, which modifies the decision-making process considering the randomness during model training and, thus, improves the performance. We build a pandemic-spreading simulator based on real-world data, serving as the experimental platform. We then conduct extensive experiments. The results show that our method outperforms all baselines, which reduces infections and deaths by 14.25% on average without the multi-agent voting method and up to 15.44% with it.
- 9 November 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 14 (1) , 1-27
Open AccessHierarchical Multi-agent Model for Reinforced Medical Resource Allocation with Imperfect Information
With the advent of the COVID-19 pandemic, the shortage in medical resources became increasingly more evident. Therefore, efficient strategies for medical resource allocation are urgently needed. However, conventional rule-based methods employed by public health experts have limited capability in dealing with the complex and dynamic pandemic-spreading situation. In addition, model-based optimization methods such as dynamic programming (DP) fail to work since we cannot obtain a precise model in real-world situations most of the time. Model-free reinforcement learning (RL) is a powerful tool for decision-making; however, three key challenges exist in solving this problem via RL: (1) complex situations and countless choices for decision-making in the real world; (2) imperfect information due to the latency of pandemic spreading; and (3) limitations on conducting experiments in the real world since we cannot set up pandemic outbreaks arbitrarily. In this article, we propose a hierarchical RL framework with several specially designed components. We design a decomposed action space with a corresponding training algorithm to deal with the countless choices, ensuring efficient and real-time strategies. We design a recurrent neural network–based framework to utilize the imperfect information obtained from the environment. We also design a multi-agent voting method, which modifies the decision-making process considering the randomness during model training and, thus, improves the performance. We build a pandemic-spreading simulator based on real-world data, serving as the experimental platform. We then conduct extensive experiments. The results show that our method outperforms all baselines, which reduces infections and deaths by 14.25% on average without the multi-agent voting method and up to 15.44% with it.
- 25 August 2022
- Published by Springer Nature in Nature Human Behaviour
- Vol. 6 (11) , 1503-1514
Strategic COVID-19 vaccine distribution can simultaneously elevate social utility and equity
Balancing social utility and equity in distributing limited vaccines is a critical policy concern for protecting against the prolonged COVID-19 pandemic and future health emergencies. What is the nature of the trade-off between maximizing collective welfare and minimizing disparities between more and less privileged communities? To evaluate vaccination strategies, we propose an epidemic model that explicitly accounts for both demographic and mobility differences among communities and their associations with heterogeneous COVID-19 risks, then calibrate it with large-scale data. Using this model, we find that social utility and equity can be simultaneously improved when vaccine access is prioritized for the most disadvantaged communities, which holds even when such communities manifest considerable vaccine reluctance. Nevertheless, equity among distinct demographic features may conflict; for example, low-income neighbourhoods might have fewer elder citizens. We design two behaviour-and-demography-aware indices, community risk and societal risk, which capture the risks communities face and those they impose on society from not being vaccinated, to inform the design of comprehensive vaccine distribution strategies. Our study provides a framework for uniting utility and equity-based considerations in vaccine distribution and sheds light on how to balance multiple ethical values in complex settings for epidemic control.
- 25 August 2022
- Published by Springer Nature in Nature Human Behaviour
- Vol. 6 (11) , 1503-1514
Strategic COVID-19 vaccine distribution can simultaneously elevate social utility and equity
Balancing social utility and equity in distributing limited vaccines is a critical policy concern for protecting against the prolonged COVID-19 pandemic and future health emergencies. What is the nature of the trade-off between maximizing collective welfare and minimizing disparities between more and less privileged communities? To evaluate vaccination strategies, we propose an epidemic model that explicitly accounts for both demographic and mobility differences among communities and their associations with heterogeneous COVID-19 risks, then calibrate it with large-scale data. Using this model, we find that social utility and equity can be simultaneously improved when vaccine access is prioritized for the most disadvantaged communities, which holds even when such communities manifest considerable vaccine reluctance. Nevertheless, equity among distinct demographic features may conflict; for example, low-income neighbourhoods might have fewer elder citizens. We design two behaviour-and-demography-aware indices, community risk and societal risk, which capture the risks communities face and those they impose on society from not being vaccinated, to inform the design of comprehensive vaccine distribution strategies. Our study provides a framework for uniting utility and equity-based considerations in vaccine distribution and sheds light on how to balance multiple ethical values in complex settings for epidemic control.