PPaperPicks

Zhiqiang Zhang

Ant Financial Services Group, Hangzhou, China

46 papers at tracked venues · 32 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. LookAhead Tuning: Safer Language Models via Partial Answer Previews
  2. Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design
  3. RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library
  4. Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
  5. Token-level Collaborative Alignment for LLM-based Generative Recommendation
  6. Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness
  7. BOSE: A Systematic Evaluation Method Optimized for Base Models
  8. Effectively PAIRing LLMs with Online Marketing via Progressive Prompting Augmentation
  9. Enhanced Insurance Claim Prediction via Decoupled Graph Neural Networks with Pseudo Labeling
  10. Explore What LLM Does Not Know in Complex Question Answering
  11. FLAG: Fraud Detection with LLM-enhanced Graph Neural Network
  12. Graph Disentangle Causal Model: Enhancing Causal Inference in Networked Observational Data
  13. GraphLAMA: Enabling Efficient Adaptation of Graph Language Models with Limited Annotations
  14. Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking
  15. IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification
  16. Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
  17. K-ON: Stacking Knowledge on the Head Layer of Large Language Model
  18. KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation
  19. MAQInstruct: Instruction-based Unified Event Relation Extraction
  20. MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
  21. Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
  22. OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System
  23. Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach
  24. Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation
  25. Stable Representation Learning on Graphs from Multiple Environments with Structure Distribution Shift
  26. Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering
  27. Adaptively Denoising Graph Neural Networks for Knowledge Distillation
  28. Calibrating Graph Neural Networks from a Data-centric Perspective
  29. Can Small Language Models be Good Reasoners for Sequential Recommendation?
  30. DDCDR: A Disentangle-based Distillation Framework for Cross-Domain Recommendation
  31. Exploiting Associations among Multi-Aspect Node Properties in Heterogeneous Graphs for Link Prediction
  32. Knowledge-augmented Financial Market Analysis and Report Generation
  33. Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs
  34. Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential Recommendation
  35. MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction
  36. MKGL: Mastery of a Three-Word Language
  37. Multi-view Temporal Knowledge Graph Reasoning
  38. Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction
  39. OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
  40. OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
  41. Optimizing Long-tailed Link Prediction in Graph Neural Networks through Structure Representation Enhancement
  42. PEACE: Prototype lEarning Augmented transferable framework for Cross-domain rEcommendation
  43. ReLand: Integrating Large Language Models' Insights into Industrial Recommenders via a Controllable Reasoning Pool
  44. Time-Sensitve Retrieval-Augmented Generation for Question Answering
  45. To Explore or Exploit? A Gradient-informed Framework to Address the Feedback Loop for Graph based Recommendation
  46. Towards Automatic Evaluation for LLMs' Clinical Capabilities: Metric, Data, and Algorithm