{"profile_id":"4n5whr0AAAAJ","profile_url":"https://scholar.google.com/citations?user=4n5whr0AAAAJ&hl=en","name":"Zhongxiang Sun","updated_at":"2026-11-09T06:48:56+00:00","citations":2278,"h_index":20,"i10_index":24,"papers":[{"id":"W7OEmFMy1HYC","title":"Uncovering ChatGPT's Capabilities in Recommender Systems","citations":526,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:W7OEmFMy1HYC"},{"id":"-f6ydRqryjwC","title":"Memory in the age of ai agents","citations":320,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:-f6ydRqryjwC"},{"id":"ULOm3_A8WrAC","title":"Redeep: Detecting hallucination in retrieval-augmented generation via mechanistic interpretability","citations":213,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:ULOm3_A8WrAC"},{"id":"Y0pCki6q_DkC","title":"A short survey of viewing large language models in legal aspect","citations":173,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:Y0pCki6q_DkC"},{"id":"KlAtU1dfN6UC","title":"Twin v2: Scaling ultra-long user behavior sequence modeling for enhanced ctr prediction at kuaishou","citations":133,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:KlAtU1dfN6UC"},{"id":"8k81kl-MbHgC","title":"Large language models enhanced collaborative filtering","citations":98,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:8k81kl-MbHgC"},{"id":"u-x6o8ySG0sC","title":"Explainable legal case matching via inverse optimal transport-based rationale extraction","citations":93,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:u-x6o8ySG0sC"},{"id":"d1gkVwhDpl0C","title":"AddrMiner: A Comprehensive Global Active IPv6 Address Discovery System","citations":86,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:d1gkVwhDpl0C"},{"id":"4TOpqqG69KYC","title":"Generative retrieval with semantic tree-structured identifiers and contrastive learning","citations":84,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:4TOpqqG69KYC"},{"id":"YsMSGLbcyi4C","title":"When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation","citations":75,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:YsMSGLbcyi4C"},{"id":"WF5omc3nYNoC","title":"KuaiSAR: A Unified Search And Recommendation Dataset","citations":72,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:WF5omc3nYNoC"},{"id":"4DMP91E08xMC","title":"Rearter: Retrieval-augmented reasoning with trustworthy process rewarding","citations":46,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:4DMP91E08xMC"},{"id":"0EnyYjriUFMC","title":"Law Article-Enhanced Legal Case Matching: a Causal Learning Approach","citations":44,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:0EnyYjriUFMC"},{"id":"ns9cj8rnVeAC","title":"Mechanistic Detection and Mitigation of Hallucination in Large Reasoning Models","citations":43,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:ns9cj8rnVeAC"},{"id":"QIV2ME_5wuYC","title":"Syler: A framework for explicit syllogistic legal reasoning in large language models","citations":38,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:QIV2ME_5wuYC"},{"id":"5nxA0vEk-isC","title":"Logic Rules as Explanations for Legal Case Retrieval","citations":30,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:5nxA0vEk-isC"},{"id":"IjCSPb-OGe4C","title":"Enhancing recommendation with search data in a causal learning manner","citations":28,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:IjCSPb-OGe4C"},{"id":"zYLM7Y9cAGgC","title":"Enough waiting for the couriers: Learning to estimate package pick-up arrival time from couriers’ spatial-temporal behaviors","citations":24,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:zYLM7Y9cAGgC"},{"id":"9ZlFYXVOiuMC","title":"Qe-rag: A robust retrieval-augmented generation benchmark for query entry errors","citations":21,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:9ZlFYXVOiuMC"},{"id":"UebtZRa9Y70C","title":"Explainable legal case matching via graph optimal transport","citations":20,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:UebtZRa9Y70C"},{"id":"7PzlFSSx8tAC","title":"Llm-empowered creator simulation for long-term evaluation of recommender systems under information asymmetry","citations":14,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:7PzlFSSx8tAC"},{"id":"j3f4tGmQtD8C","title":"Streaming hallucination detection in long chain-of-thought reasoning","citations":12,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:j3f4tGmQtD8C"},{"id":"35N4QoGY0k4C","title":"JIT-Agent: Scaling harness intelligence via just-in-time harness evolution","citations":10,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:35N4QoGY0k4C"},{"id":"YOwf2qJgpHMC","title":"LargePiG: Your Large Language Model is Secretly a Pointer Generator","citations":10,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:YOwf2qJgpHMC"},{"id":"M3NEmzRMIkIC","title":"Trigger3: Refining query correction via adaptive model selector","citations":9,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:M3NEmzRMIkIC"},{"id":"RGFaLdJalmkC","title":"Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment","citations":7,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:RGFaLdJalmkC"},{"id":"4JMBOYKVnBMC","title":"Deep search with hierarchical meta-cognitive monitoring inspired by cognitive neuroscience","citations":7,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:4JMBOYKVnBMC"},{"id":"lSLTfruPkqcC","title":"Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance","citations":6,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:lSLTfruPkqcC"},{"id":"e5wmG9Sq2KIC","title":"When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs","citations":5,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:e5wmG9Sq2KIC"},{"id":"qUcmZB5y_30C","title":"Trustworthy information retrieval in the LLM era: bias, unfairness, and hallucination","citations":5,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:qUcmZB5y_30C"},{"id":"BqipwSGYUEgC","title":"Empowering open-domain LLMs for legal document correction via legal knowledge integration and decoding constraints","citations":4,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:BqipwSGYUEgC"},{"id":"vV6vV6tmYwMC","title":"ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation","citations":4,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:vV6vV6tmYwMC"},{"id":"R3hNpaxXUhUC","title":"Beyond high-entropy exploration: Correctness-aware low-entropy segment-based advantage shaping for reasoning llms","citations":4,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:R3hNpaxXUhUC"},{"id":"GnPB-g6toBAC","title":"HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios","citations":4,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:GnPB-g6toBAC"},{"id":"kNdYIx-mwKoC","title":"Effective In-Context Example Selection through Data Compression","citations":3,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:kNdYIx-mwKoC"},{"id":"k_IJM867U9cC","title":"StyliTruth: Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering","citations":2,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:k_IJM867U9cC"},{"id":"maZDTaKrznsC","title":"Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning","citations":2,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:maZDTaKrznsC"},{"id":"3fE2CSJIrl8C","title":"To Search or to Recommend: Predicting Open-App Motivation with Neural Hawkes Process","citations":2,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:3fE2CSJIrl8C"},{"id":"JV2RwH3_ST0C","title":"DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents","citations":1,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:JV2RwH3_ST0C"},{"id":"M05iB0D1s5AC","title":"PROSE: Preservation-Constrained Selective Editing for Guilty Bias in Legal Judgment Prediction","citations":0,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:M05iB0D1s5AC"},{"id":"ldfaerwXgEUC","title":"Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges","citations":0,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:ldfaerwXgEUC"},{"id":"2P1L_qKh6hAC","title":"What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents","citations":0,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:2P1L_qKh6hAC"},{"id":"70eg2SAEIzsC","title":"Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering","citations":0,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:70eg2SAEIzsC"},{"id":"NaGl4SEjCO4C","title":"NeuroCogMap Reveals Cognitive Organization of Large Language Models","citations":0,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:NaGl4SEjCO4C"},{"id":"blknAaTinKkC","title":"Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm","citations":0,"url":"https://scholar.google.com/citations?view_op=view_citation&hl=en&user=4n5whr0AAAAJ&pagesize=100&citation_for_view=4n5whr0AAAAJ:blknAaTinKkC"}]}