187 citations · 392 across the 26 of their papers we have counts for
27 papers
ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation
Jiahao Zhao, Xiaomin Yu, Zhongxiang Sun +5
Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require complex semantic understanding, multi-step reasoning, an…
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Haoyu Wang, Yifan Shang, Zhongxiang Sun +3
Continual Pre-Training (CPT) is essential for enabling Language Models (LMs) to integrate new knowledge without erasing old. While classical CPT techniques like data replay have be…
HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios
Jiayue Pu, Zhongxiang Sun, Zilu Zhang +2
The rapid evolution of embodied agents has accelerated the deployment of household robots in real-world environments. However, unlike structured industrial settings, household spac…
DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents
Jiahao Zhao, Shaoxuan Xu, Zhongxiang Sun +6
Recently, Diffusion Large Language Models (dLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation pa…
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
Zhongxiang Sun, Yi Zhan, Chenglei Shen +4
Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We…
Memory in the Age of AI Agents
Yuyang Hu, Shichun Liu, Yanwei Yue +44
Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attentio…
Balancing Stylization and Truth via Disentangled Representation Steering
Chenglei Shen, Zhongxiang Sun, Teng Shi +2
Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off:…
An Explicit Syllogistic Legal Reasoning Framework for Large Language Models
Kepu Zhang, Weijie Yu, Zhongxiang Sun +1
Syllogistic reasoning is crucial for sound legal decision-making, allowing legal professionals to draw logical conclusions by applying general principles to specific case facts. Wh…
Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
Zhongxiang Sun, Qipeng Wang, Haoyu Wang +2
Large Reasoning Models (LRMs) have shown impressive capabilities in multi-step reasoning tasks. However, alongside these successes, a more deceptive form of model error has emerged…
QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors
Kepu Zhang, Zhongxiang Sun, Weijie Yu +5
Retriever-augmented generation (RAG) has become a widely adopted approach for enhancing the factual accuracy of large language models (LLMs). While current benchmarks evaluate the…
CreAgent: Towards Long-Term Evaluation of Recommender System under Platform-Creator Information Asymmetry
Xiaopeng Ye, Chen Xu, Zhongxiang Sun +4
Ensuring the long-term sustainability of recommender systems (RS) emerges as a crucial issue. Traditional offline evaluation methods for RS typically focus on immediate user feedba…
ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding
Zhongxiang Sun, Qipeng Wang, Weijie Yu +6
Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While…
Trigger: Refining Query Correction via Adaptive Model Selector
Kepu Zhang, Zhongxiang Sun, Xiao Zhang +4
In search scenarios, user experience can be hindered by erroneous queries due to typos, voice errors, or knowledge gaps. Therefore, query correction is crucial for search engines.…
LargePiG: Your Large Language Model is Secretly a Pointer Generator
Zhongxiang Sun, Zihua Si, Xiaoxue Zang +4
Recent research on query generation has focused on using Large Language Models (LLMs), which despite bringing state-of-the-art performance, also introduce issues with hallucination…
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
Zhongxiang Sun, Xiaoxue Zang, Kai Zheng +5
Retrieval-Augmented Generation (RAG) models are designed to incorporate external knowledge, reducing hallucinations caused by insufficient parametric (internal) knowledge. However,…
TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou
Zihua Si, Lin Guan, ZhongXiang Sun +12
The significance of modeling long-term user interests for CTR prediction tasks in large-scale recommendation systems is progressively gaining attention among researchers and practi…
Effective In-Context Example Selection through Data Compression
Zhongxiang Sun, Kepu Zhang, Haoyu Wang +2
In-context learning has been extensively validated in large language models. However, the mechanism and selection strategy for in-context example selection, which is a crucial ingr…
To Search or to Recommend: Predicting Open-App Motivation with Neural Hawkes Process
Zhongxiang Sun, Zihua Si, Xiao Zhang +4
Incorporating Search and Recommendation (S&R) services within a singular application is prevalent in online platforms, leading to a new task termed open-app motivation prediction,…
Logic Rules as Explanations for Legal Case Retrieval
Zhongxiang Sun, Kepu Zhang, Weijie Yu +2
In this paper, we address the issue of using logic rules to explain the results from legal case retrieval. The task is critical to legal case retrieval because the users (e.g., law…
Large Language Models Enhanced Collaborative Filtering
Zhongxiang Sun, Zihua Si, Xiaoxue Zang +4
Recent advancements in Large Language Models (LLMs) have attracted considerable interest among researchers to leverage these models to enhance Recommender Systems (RSs). Existing w…
Generative Retrieval with Semantic Tree-Structured Item Identifiers via Contrastive Learning
Zihua Si, Zhongxiang Sun, Jiale Chen +7
The retrieval phase is a vital component in recommendation systems, requiring the model to be effective and efficient. Recently, generative retrieval has become an emerging paradig…
KuaiSAR: A Unified Search And Recommendation Dataset
Zhongxiang Sun, Zihua Si, Xiaoxue Zang +5
The confluence of Search and Recommendation (S&R) services is vital to online services, including e-commerce and video platforms. The integration of S&R modeling is a highly intuit…
When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation
Zihua Si, Zhongxiang Sun, Xiao Zhang +5
Modern online service providers such as online shopping platforms often provide both search and recommendation (S&R) services to meet different user needs. Rarely has there been an…
Uncovering ChatGPT's Capabilities in Recommender Systems
Sunhao Dai, Ninglu Shao, Haiyuan Zhao +6
The debut of ChatGPT has recently attracted the attention of the natural language processing (NLP) community and beyond. Existing studies have demonstrated that ChatGPT shows signi…