Shen Gao
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
Research Subjects
Shen Gao has a total of 73 co-authors. Here are the top co-authors by number of shared publications:
- Xiuying Chen
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
6 shared publications - Xiangliang Zhang
University of Notre Dame
5 shared publications - Xin Gao
King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
5 shared publications - Mingzhe Li
Ant Group, Beijing, China
4 shared publications - Shuo Shang
University of Electronic Science and Technology of China, Chengdu, Sichuan, China
4 shared publications - Zhaochun Ren
Leiden University
4 shared publications
Latest Publications
- Open Access
- 23 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44  (7) , 1-41
LLMs Are Also Effective Embedding Models: An In-depth Overview
Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift from traditional encoder-only models like ELMo and BERT to decoder-only, large-scale LLMs such as GPT, LLaMA, and Mistral. This survey provides an in-depth overview of this transition, beginning with foundational techniques before the LLM era, followed by LLM-based embedding models through two main strategies to derive embeddings from LLMs. (1) Direct prompting: We mainly discuss the prompt designs and the underlying rationale for deriving competitive embeddings. (2) Data-centric tuning: We cover extensive aspects that affect tuning an embedding model, including model architecture, training objectives, data construction, and so on. Upon the above, we also cover advanced methods for producing embeddings from longer texts, multilingual, code, cross-modal data, as well as reasoning-aware and other domain-specific scenarios. Furthermore, we discuss factors affecting choices of embedding models, such as performance comparisons, dense vs. sparse embeddings, pooling strategies, and scaling laws. Lastly, the survey highlights the limitations and challenges in adapting LLMs for embeddings, including cross-task embedding quality, tradeoffs between efficiency and accuracy, low-resource, long-context, data bias, robustness, and so on. This survey serves as a valuable resource for researchers and practitioners by synthesizing current advancements, highlighting key challenges, and offering a comprehensive framework for future work aimed at enhancing the effectiveness and efficiency of LLMs as embedding models.
- 23 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44  (7) , 1-41
Open AccessLLMs Are Also Effective Embedding Models: An In-depth Overview
Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift from traditional encoder-only models like ELMo and BERT to decoder-only, large-scale LLMs such as GPT, LLaMA, and Mistral. This survey provides an in-depth overview of this transition, beginning with foundational techniques before the LLM era, followed by LLM-based embedding models through two main strategies to derive embeddings from LLMs. (1) Direct prompting: We mainly discuss the prompt designs and the underlying rationale for deriving competitive embeddings. (2) Data-centric tuning: We cover extensive aspects that affect tuning an embedding model, including model architecture, training objectives, data construction, and so on. Upon the above, we also cover advanced methods for producing embeddings from longer texts, multilingual, code, cross-modal data, as well as reasoning-aware and other domain-specific scenarios. Furthermore, we discuss factors affecting choices of embedding models, such as performance comparisons, dense vs. sparse embeddings, pooling strategies, and scaling laws. Lastly, the survey highlights the limitations and challenges in adapting LLMs for embeddings, including cross-task embedding quality, tradeoffs between efficiency and accuracy, low-resource, long-context, data bias, robustness, and so on. This survey serves as a valuable resource for researchers and practitioners by synthesizing current advancements, highlighting key challenges, and offering a comprehensive framework for future work aimed at enhancing the effectiveness and efficiency of LLMs as embedding models.
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1633-1643
FAVE: Flow-based Average Velocity Establishment for Sequential Recommendation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1633-1643
Open AccessFAVE: Flow-based Average Velocity Establishment for Sequential Recommendation
- 3 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37  (11) , 6582-6596
Personalized Review Summarization by Using Graph-Based Retrieval Augmemted Generation
Review summarization aims to provide a summary that covers the main aspect of the product review and reflects personal preference. Existing methods employ the historical reviews of customer and product to provide useful clues for the target summary generation. However, most of the existing methods indiscriminately model the historical reviews of customer and product. Since the historical customer reviews provide the personal information while the historical product reviews provide the commonly focused aspect of the product, these two types of heterogeneous information should be separately modeled. Moreover, the review rating of the historical reviews can be seen as a high-level abstraction of the customer preference and product which have been ignored by most of the existing methods. In this paper, we propose the Heterogeneous Historical Review aware Review Summarization (HHRRS) which separately models the two types of historical reviews with the rating information by a graph reasoning module with a contrastive loss. We employ a multi-task paradigm that conducts the review sentiment classification and summarization (GRARS) to model the two types of heterogeneous information in a fine-grained manner. We conduct extensive experiments on four benchmark datasets, and demonstrate the superiority of HHRRS on both tasks.
- 3 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37  (11) , 6582-6596
Personalized Review Summarization by Using Graph-Based Retrieval Augmemted Generation
Review summarization aims to provide a summary that covers the main aspect of the product review and reflects personal preference. Existing methods employ the historical reviews of customer and product to provide useful clues for the target summary generation. However, most of the existing methods indiscriminately model the historical reviews of customer and product. Since the historical customer reviews provide the personal information while the historical product reviews provide the commonly focused aspect of the product, these two types of heterogeneous information should be separately modeled. Moreover, the review rating of the historical reviews can be seen as a high-level abstraction of the customer preference and product which have been ignored by most of the existing methods. In this paper, we propose the Heterogeneous Historical Review aware Review Summarization (HHRRS) which separately models the two types of historical reviews with the rating information by a graph reasoning module with a contrastive loss. We employ a multi-task paradigm that conducts the review sentiment classification and summarization (GRARS) to model the two types of heterogeneous information in a fine-grained manner. We conduct extensive experiments on four benchmark datasets, and demonstrate the superiority of HHRRS on both tasks.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2904-2914
Generative Next POI Recommendation with Semantic ID
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2904-2914
Open AccessGenerative Next POI Recommendation with Semantic ID
- Open Access
- 16 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43  (4) , 1-25
New Paradigm for Evaluating Scholar Summaries: A Facet-aware Metric and a Meta-evaluation Benchmark
Evaluation of summary quality is particularly crucial within the scientific domain, because it facilitates efficient knowledge dissemination and automated scientific information retrieval. This article presents conceptual and experimental analyses of scientific summarization, highlighting the inadequacies of traditional evaluation methods. These methods, including \( n \) -gram overlap calculations, embedding comparisons, verification, and QA-based approaches, often fall short in providing explanations, grasping scientific concepts, or identifying key content. Correspondingly, we introduce the Facet-aware Metric (FM), employing LLMs for advanced semantic matching to evaluate summaries based on different facets. The facet granularity is tailored to the structure of scientific abstracts, offering an integrated evaluation approach that is not fragmented, while also providing fine-grained interpretability. Recognizing the absence of an evaluation benchmark in the scientific domain, we curate a Scientific abstract summary evaluation Dataset (ScholarSum) with facet-level annotations. Our findings confirm that FM offers a more logical approach to evaluating scientific summaries. In addition, fine-tuned smaller models can compete with LLMs in scientific contexts, while LLMs have limitations in learning from in-context information in scientific domains. We hope our benchmark inspires better evaluation metrics and future enhancements to LLMs: https://github.com/iriscxy/ScholarSum .- 16 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43  (4) , 1-25
Open AccessNew Paradigm for Evaluating Scholar Summaries: A Facet-aware Metric and a Meta-evaluation Benchmark
Evaluation of summary quality is particularly crucial within the scientific domain, because it facilitates efficient knowledge dissemination and automated scientific information retrieval. This article presents conceptual and experimental analyses of scientific summarization, highlighting the inadequacies of traditional evaluation methods. These methods, including \( n \) -gram overlap calculations, embedding comparisons, verification, and QA-based approaches, often fall short in providing explanations, grasping scientific concepts, or identifying key content. Correspondingly, we introduce the Facet-aware Metric (FM), employing LLMs for advanced semantic matching to evaluate summaries based on different facets. The facet granularity is tailored to the structure of scientific abstracts, offering an integrated evaluation approach that is not fragmented, while also providing fine-grained interpretability. Recognizing the absence of an evaluation benchmark in the scientific domain, we curate a Scientific abstract summary evaluation Dataset (ScholarSum) with facet-level annotations. Our findings confirm that FM offers a more logical approach to evaluating scientific summaries. In addition, fine-tuned smaller models can compete with LLMs in scientific contexts, while LLMs have limitations in learning from in-context information in scientific domains. We hope our benchmark inspires better evaluation metrics and future enhancements to LLMs: https://github.com/iriscxy/ScholarSum . - Top Cited PapersOpen Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2222-2237
Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2222-2237
Top Cited PapersOpen AccessTool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
- 30 December 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 310
SMSMO: Learning to generate multimodal summary for scientific papers
- 30 December 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 310
SMSMO: Learning to generate multimodal summary for scientific papers
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37  (2) , 991-1003
Unified Multi-Scenario Summarization Evaluation and Explanation
Summarization quality evaluation is a non-trivial task in text summarization. Contemporary methods can be mainly categorized into two scenarios: (1) reference-based: evaluating with human-labeled reference summary; (2) reference-free: evaluating the summary consistency of the document. Recent studies mainly focus on one of these scenarios and explore training neural models to align with human criteria and finally give a numeric score. However, the models from different scenarios are optimized individually, which may result in sub-optimal performance since they neglect the shared knowledge across different scenarios. Besides, designing individual models for each scenario caused inconvenience to the user. Moreover, only providing the numeric quality evaluation score for users cannot help users to improve the summarization model, since they do not know why the score is low. Inspired by this, we propose Unified Multi-scenario Summarization Evaluator (UMSE) and Multi-Agent Summarization Evaluation Explainer (MASEE). More specifically, we propose a perturbed prefix tuning method to share cross-scenario knowledge between scenarios and use a self-supervised training paradigm to optimize the model without extra human labeling. Our UMSE is the first unified summarization evaluation framework engaged with the ability to be used in three evaluation scenarios. We propose a multi-agent summary evaluation explanation method MASEE, which employs several LLM-based agents to generate detailed natural language explanations in four different aspects. Experimental results across three typical scenarios on the benchmark dataset SummEval indicate that our UMSE can achieve comparable performance with several existing strong methods that are specifically designed for each scenario. And intensive quantitative and qualitative experiments also demonstrate the effectiveness of our proposed explanation method, which can generate consistent and accurate explanations.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37  (2) , 991-1003
Unified Multi-Scenario Summarization Evaluation and Explanation
Summarization quality evaluation is a non-trivial task in text summarization. Contemporary methods can be mainly categorized into two scenarios: (1) reference-based: evaluating with human-labeled reference summary; (2) reference-free: evaluating the summary consistency of the document. Recent studies mainly focus on one of these scenarios and explore training neural models to align with human criteria and finally give a numeric score. However, the models from different scenarios are optimized individually, which may result in sub-optimal performance since they neglect the shared knowledge across different scenarios. Besides, designing individual models for each scenario caused inconvenience to the user. Moreover, only providing the numeric quality evaluation score for users cannot help users to improve the summarization model, since they do not know why the score is low. Inspired by this, we propose Unified Multi-scenario Summarization Evaluator (UMSE) and Multi-Agent Summarization Evaluation Explainer (MASEE). More specifically, we propose a perturbed prefix tuning method to share cross-scenario knowledge between scenarios and use a self-supervised training paradigm to optimize the model without extra human labeling. Our UMSE is the first unified summarization evaluation framework engaged with the ability to be used in three evaluation scenarios. We propose a multi-agent summary evaluation explanation method MASEE, which employs several LLM-based agents to generate detailed natural language explanations in four different aspects. Experimental results across three typical scenarios on the benchmark dataset SummEval indicate that our UMSE can achieve comparable performance with several existing strong methods that are specifically designed for each scenario. And intensive quantitative and qualitative experiments also demonstrate the effectiveness of our proposed explanation method, which can generate consistent and accurate explanations.
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2018-2027
Flexible and Adaptable Summarization via Expertise Separation
A proficient summarization model should exhibit both flexibility -- the capacity to handle a range of in-domain summarization tasks, and adaptability -- the competence to acquire new knowledge and adjust to unseen out-of-domain tasks. Unlike large language models (LLMs) that achieve this through parameter scaling, we propose a more parameter-efficient approach in this study. Our motivation rests on the principle that the general summarization ability to capture salient information can be shared across different tasks, while the domain-specific summarization abilities need to be distinct and tailored. Concretely, we propose MoeSumm, a Mixture-of-Expert Summarization architecture, which utilizes a main expert for gaining the general summarization capability and deputy experts that selectively collaborate to meet specific summarization task requirements. We further propose a max-margin loss to stimulate the separation of these abilities. Our model's distinct separation of general and domain-specific summarization abilities grants it with notable flexibility and adaptability, all while maintaining parameter efficiency. MoeSumm achieves flexibility by managing summarization across multiple domains with a single model, utilizing a shared main expert and selected deputy experts. It exhibits adaptability by tailoring deputy experts to cater to out-of-domain few-shot and zero-shot scenarios. Experimental results on 11 datasets show the superiority of our model compared with recent baselines and LLMs. We also provide statistical and visual evidence of the distinct separation of the two abilities in MoeSumm https://github.com/iriscxy/MoE_Summ
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2018-2027
Open AccessFlexible and Adaptable Summarization via Expertise Separation
A proficient summarization model should exhibit both flexibility -- the capacity to handle a range of in-domain summarization tasks, and adaptability -- the competence to acquire new knowledge and adjust to unseen out-of-domain tasks. Unlike large language models (LLMs) that achieve this through parameter scaling, we propose a more parameter-efficient approach in this study. Our motivation rests on the principle that the general summarization ability to capture salient information can be shared across different tasks, while the domain-specific summarization abilities need to be distinct and tailored. Concretely, we propose MoeSumm, a Mixture-of-Expert Summarization architecture, which utilizes a main expert for gaining the general summarization capability and deputy experts that selectively collaborate to meet specific summarization task requirements. We further propose a max-margin loss to stimulate the separation of these abilities. Our model's distinct separation of general and domain-specific summarization abilities grants it with notable flexibility and adaptability, all while maintaining parameter efficiency. MoeSumm achieves flexibility by managing summarization across multiple domains with a single model, utilizing a shared main expert and selected deputy experts. It exhibits adaptability by tailoring deputy experts to cater to out-of-domain few-shot and zero-shot scenarios. Experimental results on 11 datasets show the superiority of our model compared with recent baselines and LLMs. We also provide statistical and visual evidence of the distinct separation of the two abilities in MoeSumm https://github.com/iriscxy/MoE_Summ
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 3444-3453
Generative News Recommendation
Most existing news recommendation methods tackle this task by conducting semantic matching between candidate news and user representation produced by historical clicked news. However, they overlook the high-level connections among different news articles and also ignore the profound relationship between these news articles and users. And the definition of these methods dictates that they can only deliver news articles as-is. On the contrary, integrating several relevant news articles into a coherent narrative would assist users in gaining a quicker and more comprehensive understanding of events. In this paper, we propose a novel generative news recommendation paradigm that includes two steps: (1) Leveraging the internal knowledge and reasoning capabilities of the Large Language Model (LLM) to perform high-level matching between candidate news and user representation; (2) Generating a coherent and logically structured narrative based on the associations between related news and user interests, thus engaging users in further reading of the news. Specifically, we propose GNR to implement the generative news recommendation paradigm. First, we compose the dual-level representation of news and users by leveraging LLM to generate theme-level representations and combine them with semantic-level representations. Next, in order to generate a coherent narrative, we explore the news relation and filter the related news according to the user preference. Finally, we propose a novel training method named UIFT to train the LLM to fuse multiple news articles in a coherent narrative. Extensive experiments show that GNR can improve recommendation accuracy and eventually generate more personalized and factually consistent narratives.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 3444-3453
Open AccessGenerative News Recommendation
Most existing news recommendation methods tackle this task by conducting semantic matching between candidate news and user representation produced by historical clicked news. However, they overlook the high-level connections among different news articles and also ignore the profound relationship between these news articles and users. And the definition of these methods dictates that they can only deliver news articles as-is. On the contrary, integrating several relevant news articles into a coherent narrative would assist users in gaining a quicker and more comprehensive understanding of events. In this paper, we propose a novel generative news recommendation paradigm that includes two steps: (1) Leveraging the internal knowledge and reasoning capabilities of the Large Language Model (LLM) to perform high-level matching between candidate news and user representation; (2) Generating a coherent and logically structured narrative based on the associations between related news and user interests, thus engaging users in further reading of the news. Specifically, we propose GNR to implement the generative news recommendation paradigm. First, we compose the dual-level representation of news and users by leveraging LLM to generate theme-level representations and combine them with semantic-level representations. Next, in order to generate a coherent narrative, we explore the news relation and filter the related news according to the user preference. Finally, we propose a novel training method named UIFT to train the LLM to fuse multiple news articles in a coherent narrative. Extensive experiments show that GNR can improve recommendation accuracy and eventually generate more personalized and factually consistent narratives.