Kuicai Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kuicai Dong has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Yichao Wang
Huawei Technologies Ltd., Shenzhen, China
4 shared publications - Gang Wang
Huawei Technologies Co., Ltd., Shenzhen, China
3 shared publications - Xiangyu Zhao
City University of Hong Kong, Kowloon Tong, Hong Kong
3 shared publications - Xiaopeng Li
City University of Hong Kong, Hong Kong, China
3 shared publications - Yong Liu
Huawei Technologies, Shanghai, China
3 shared publications - Huifeng Guo
Huawei Technologies, Shenzhen, China
2 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6688-6699
When Hard Negatives Hurt: Bridging the Generative Discriminative Gap in Hard Negative Synthesis for Retrieval
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6688-6699
Open AccessWhen Hard Negatives Hurt: Bridging the Generative Discriminative Gap in Hard Negative Synthesis for Retrieval
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 668-678
FollowTable: A Benchmark for Instruction-Following Table Retrieval
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 668-678
Open AccessFollowTable: A Benchmark for Instruction-Following Table Retrieval
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2878-2889
Exploring Recommender System Evaluation: A Multi-Modal LLM Agent Framework for A/B Testing
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2878-2889
Open AccessExploring Recommender System Evaluation: A Multi-Modal LLM Agent Framework for A/B Testing
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2049-2059
To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents suffer from critical inefficiency: they conduct excessive searches as they cannot accurately judge when to stop searching and start answering. This stems from outcome-centric training that prioritize final results over the search process itself. We identify the root cause as misaligned decision boundaries, the threshold determining when accumulated information suffices to answer. This causes over-search (redundant searching despite sufficient knowledge) and under-search (premature termination yielding incorrect answers). To address these errors, we propose a comprehensive framework comprising two key components. First, we introduce causal intervention-based diagnosis that identifies boundary errors by comparing factual and counterfactual trajectories at each decision point. Second, we develop Decision Boundary Alignment for Deep Search agents (DAS), which constructs preference datasets from causal feedback and aligns policies via preference optimization. Experiments on public datasets demonstrate that decision boundary errors are pervasive across state-of-the-art agents. Our DAS method effectively calibrates these boundaries, mitigating both over-search and under-search to achieve substantial gains in accuracy and efficiency. Our code and data are publicly available at: https://github.com/Applied-Machine-Learning-Lab/WWW2026_DAS.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2049-2059
Open AccessTo Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents suffer from critical inefficiency: they conduct excessive searches as they cannot accurately judge when to stop searching and start answering. This stems from outcome-centric training that prioritize final results over the search process itself. We identify the root cause as misaligned decision boundaries, the threshold determining when accumulated information suffices to answer. This causes over-search (redundant searching despite sufficient knowledge) and under-search (premature termination yielding incorrect answers). To address these errors, we propose a comprehensive framework comprising two key components. First, we introduce causal intervention-based diagnosis that identifies boundary errors by comparing factual and counterfactual trajectories at each decision point. Second, we develop Decision Boundary Alignment for Deep Search agents (DAS), which constructs preference datasets from causal feedback and aligns policies via preference optimization. Experiments on public datasets demonstrate that decision boundary errors are pervasive across state-of-the-art agents. Our DAS method effectively calibrates these boundaries, mitigating both over-search and under-search to achieve substantial gains in accuracy and efficiency. Our code and data are publicly available at: https://github.com/Applied-Machine-Learning-Lab/WWW2026_DAS.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2349-2360
Doc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research
Deep Research systems have revolutionized how LLMs solve complex questions through iterative reasoning and evidence gathering. However, current systems remain fundamentally constrained to textual web data, overlooking the vast knowledge embedded in multimodal documents: scientific papers, technical reports, and financial documents where critical information exists in figures, tables, charts, and equations. Processing such documents demands sophisticated parsing to preserve visual semantics, intelligent chunking to maintain structural coherence, and adaptive retrieval across modalities, which are capabilities absent in existing systems. In response, we present Doc-Researcher, a unified system that bridges this gap through three integrated components: (i) deep multimodal parsing that preserves layout structure and visual semantics while creating multi-granular representations from chunk to document level, (ii) systematic retrieval architecture supporting text-only, vision-only, and hybrid paradigms with dynamic granularity selection, and (iii) iterative multi-agent workflows that decompose complex queries, progressively accumulate evidence, and synthesize comprehensive answers across documents and modalities. To enable rigorous evaluation, we introduce M4DocBench, the first benchmark for Multi-modal, Multi-hop, Multi-document, and Multi-turn deep research. Featuring 158 expert-annotated questions with complete evidence chains across 304 documents, M4DocBench tests capabilities that existing benchmarks cannot assess. Experiments demonstrate that Doc-Researcher achieves 50.6% accuracy, 3.4× better than state-of-the-art baselines, validating that effective document research requires not just better retrieval, but fundamentally deep parsing that preserve multimodal integrity and support iterative research. Our work establishes a new paradigm for conducting deep research on multimodal document collections.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2349-2360
Open AccessDoc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research
Deep Research systems have revolutionized how LLMs solve complex questions through iterative reasoning and evidence gathering. However, current systems remain fundamentally constrained to textual web data, overlooking the vast knowledge embedded in multimodal documents: scientific papers, technical reports, and financial documents where critical information exists in figures, tables, charts, and equations. Processing such documents demands sophisticated parsing to preserve visual semantics, intelligent chunking to maintain structural coherence, and adaptive retrieval across modalities, which are capabilities absent in existing systems. In response, we present Doc-Researcher, a unified system that bridges this gap through three integrated components: (i) deep multimodal parsing that preserves layout structure and visual semantics while creating multi-granular representations from chunk to document level, (ii) systematic retrieval architecture supporting text-only, vision-only, and hybrid paradigms with dynamic granularity selection, and (iii) iterative multi-agent workflows that decompose complex queries, progressively accumulate evidence, and synthesize comprehensive answers across documents and modalities. To enable rigorous evaluation, we introduce M4DocBench, the first benchmark for Multi-modal, Multi-hop, Multi-document, and Multi-turn deep research. Featuring 158 expert-annotated questions with complete evidence chains across 304 documents, M4DocBench tests capabilities that existing benchmarks cannot assess. Experiments demonstrate that Doc-Researcher achieves 50.6% accuracy, 3.4× better than state-of-the-art baselines, validating that effective document research requires not just better retrieval, but fundamentally deep parsing that preserve multimodal integrity and support iterative research. Our work establishes a new paradigm for conducting deep research on multimodal document collections.
- Top Cited PapersOpen Access
- 10 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (5) , 1-33
A Unified Framework for Multi-Domain CTR Prediction via Large Language Models
Multi-Domain Click-Through Rate (MDCTR) prediction is crucial for online recommendation platforms, which involves providing personalized recommendation services to users in different domains. However, current MDCTR models are confronted with the following limitations. Firstly, due to varying data sparsity in different domains, models can easily be dominated by some specific domains, which leads to significant performance degradation in other domains (i.e., the “seesaw phenomenon”). Secondly, when new domain emerges, the scalability of existing methods is limited, making it difficult to adapt to the dynamic growth of the domain. Traditional MDCTR models usually use one-hot encoding for semantic information such as product titles, thus losing rich semantic information and leading to insufficient generalization of the model. In this article, we propose a novel solution Uni-CTR to address these challenges. Uni-CTR leverages Large Language Model (LLM) to extract layer-wise semantic representations that capture domain commonalities, mitigating the seesaw phenomenon and enhancing generalization. Besides, it incorporates a pluggable domain-specific network to capture domain characteristics, ensuring scalability to dynamic domain growth. Experimental results on public datasets and industrial scenarios show that Uni-CTR significantly outperforms state-of-the-art (SOTA) models. In addition, Uni-CTR shows significant results in zero shot prediction. Code is available at Applied Machine Learning Lab (Pytorch), GitHub (Pytorch) and Gitee (MindSpore).
- 10 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (5) , 1-33
Top Cited PapersOpen AccessA Unified Framework for Multi-Domain CTR Prediction via Large Language Models
Multi-Domain Click-Through Rate (MDCTR) prediction is crucial for online recommendation platforms, which involves providing personalized recommendation services to users in different domains. However, current MDCTR models are confronted with the following limitations. Firstly, due to varying data sparsity in different domains, models can easily be dominated by some specific domains, which leads to significant performance degradation in other domains (i.e., the “seesaw phenomenon”). Secondly, when new domain emerges, the scalability of existing methods is limited, making it difficult to adapt to the dynamic growth of the domain. Traditional MDCTR models usually use one-hot encoding for semantic information such as product titles, thus losing rich semantic information and leading to insufficient generalization of the model. In this article, we propose a novel solution Uni-CTR to address these challenges. Uni-CTR leverages Large Language Model (LLM) to extract layer-wise semantic representations that capture domain commonalities, mitigating the seesaw phenomenon and enhancing generalization. Besides, it incorporates a pluggable domain-specific network to capture domain characteristics, ensuring scalability to dynamic domain growth. Experimental results on public datasets and industrial scenarios show that Uni-CTR significantly outperforms state-of-the-art (SOTA) models. In addition, Uni-CTR shows significant results in zero shot prediction. Code is available at Applied Machine Learning Lab (Pytorch), GitHub (Pytorch) and Gitee (MindSpore).
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1565-1574
Collaborative Cross-modal Fusion with Large Language Model for Recommendation
Despite the success of conventional collaborative filtering (CF) approaches for recommendation systems, they exhibit limitations in leveraging semantic knowledge within the textual attributes of users and items. Recent focus on the application of large language models for recommendation (LLM4Rec) has highlighted their capability for effective semantic knowledge capture. However, these methods often overlook the collaborative signals in user behaviors. Some simply instruct-tune a language model, while others directly inject the embeddings of a CF-based model, lacking a synergistic fusion of different modalities. To address these issues, we propose a framework of Collaborative Cross-modal Fusion with Large Language Models, termed CCF-LLM, for recommendation. In this framework, we translate the user-item interactions into a hybrid prompt to encode both semantic knowledge and collaborative signals, and then employ an attentive cross-modal fusion strategy to effectively fuse latent embeddings of both modalities. Extensive experiments demonstrate that CCF-LLM outperforms existing methods by effectively utilizing semantic and collaborative signals in the LLM4Rec context.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1565-1574
Open AccessCollaborative Cross-modal Fusion with Large Language Model for Recommendation
Despite the success of conventional collaborative filtering (CF) approaches for recommendation systems, they exhibit limitations in leveraging semantic knowledge within the textual attributes of users and items. Recent focus on the application of large language models for recommendation (LLM4Rec) has highlighted their capability for effective semantic knowledge capture. However, these methods often overlook the collaborative signals in user behaviors. Some simply instruct-tune a language model, while others directly inject the embeddings of a CF-based model, lacking a synergistic fusion of different modalities. To address these issues, we propose a framework of Collaborative Cross-modal Fusion with Large Language Models, termed CCF-LLM, for recommendation. In this framework, we translate the user-item interactions into a hybrid prompt to encode both semantic knowledge and collaborative signals, and then employ an attentive cross-modal fusion strategy to effectively fuse latent embeddings of both modalities. Extensive experiments demonstrate that CCF-LLM outperforms existing methods by effectively utilizing semantic and collaborative signals in the LLM4Rec context.
- Open Access
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 1204-1207
DOCoR: Document-level OpenIE with Coreference Resolution
Open Information Extraction (OpenIE) extracts relational fact tuples in the form of from text. Most existing OpenIE solutions operate at sentence level and extract relational tuples solely from a sentence. However, many sentences exist as a part of paragraph or a document, where coreferencing is common. In this demonstration, we present a system which refines the semantic tuples generated by OpenIE with the aid of a coreference resolution tool. Specifically, all coreferential mentions across the entire document are identified and grouped into coreferential clusters. Objects and subjects in the extracted tuples from OpenIE which match any coreferential mentions are then resolved with a suitable representative term. In this way, our system is able to resolve both anaphoric and cataphoric references, to achieve Document-level OpenIE with Coreference Resolution (DOCoR). The demonstration video can be viewed at https://youtu.be/o9ZSWCBvlDs
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 1204-1207
Open AccessDOCoR: Document-level OpenIE with Coreference Resolution
Open Information Extraction (OpenIE) extracts relational fact tuples in the form of from text. Most existing OpenIE solutions operate at sentence level and extract relational tuples solely from a sentence. However, many sentences exist as a part of paragraph or a document, where coreferencing is common. In this demonstration, we present a system which refines the semantic tuples generated by OpenIE with the aid of a coreference resolution tool. Specifically, all coreferential mentions across the entire document are identified and grouped into coreferential clusters. Objects and subjects in the extracted tuples from OpenIE which match any coreferential mentions are then resolved with a suitable representative term. In this way, our system is able to resolve both anaphoric and cataphoric references, to achieve Document-level OpenIE with Coreference Resolution (DOCoR). The demonstration video can be viewed at https://youtu.be/o9ZSWCBvlDs