Xiao Ding

Venues

Frequent coauthors

Papers

1. Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
   ACL 2026 ·

   Yang Zhao

   DBLP profile ↗ORCID search ↗
2. Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark
   ACL 2026 ·

   Zihan Zhang

   DBLP profile ↗ORCID search ↗
3. Large Language Models Are Still Misled by Simple Bias Ensembles
   ACL 2026 ·

   Zhouhao Sun

   DBLP profile ↗ORCID search ↗
4. MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
   ACL 2026 ·

   Yang Zhao

   DBLP profile ↗ORCID search ↗
5. MDC-Bench: A Multidisciplinary Causal Benchmark Based on Causal Structures for Evaluating Large Language Models
   ACL 2026 ·

   Peng Wang

   DBLP profile ↗ORCID search ↗
6. TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles
   ACL 2026 ·

   Yirong Zeng

   DBLP profile ↗ORCID search ↗
7. Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns
   ACL 2025 ·

   Yang Zhao

   DBLP profile ↗ORCID search ↗
8. Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection
   ACL 2025 ·

   Yang Zhao

   DBLP profile ↗ORCID search ↗
9. Com² : A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models
   ACL 2025 ·

   Kai Xiong

   DBLP profile ↗ORCID search ↗
10. ExpeTrans: LLMs Are Experiential Transfer Learners
    ACL 2025 ·

    Jinglong Gao

    DBLP profile ↗ORCID search ↗
11. Exploring Large Language Models for Effective Rumor Detection on Social Media
    NAACL 2025 ·

    Yirong Zeng

    DBLP profile ↗ORCID search ↗
12. Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation
    ACL 2025 ·

    Jihao Shi

    DBLP profile ↗ORCID search ↗
13. Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
    EMNLP 2025 ·

    Yirong Zeng

    DBLP profile ↗ORCID search ↗
14. Towards Transferable Personality Representation Learning based on Triplet Comparisons and Its Applications
    EMNLP 2025 ·

    Kai Tang

    DBLP profile ↗ORCID search ↗
15. UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection
    NeurIPS 2025 ·

    Yang Zhao

    DBLP profile ↗ORCID search ↗
16. iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use
    EMNLP 2025 ·

    Yirong Zeng

    DBLP profile ↗ORCID search ↗
17. Causal-Guided Active Learning for Debiasing Large Language Models
    ACL 2024 ·

    Zhouhao Sun

    DBLP profile ↗ORCID search ↗
18. Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning
    ACL 2024 ·

    Yang Zhao

    DBLP profile ↗ORCID search ↗
19. Learning Geometry-Aware Representations for New Intent Discovery
    ACL 2024 ·

    Kai Tang

    DBLP profile ↗ORCID search ↗
20. Link Prediction in Multilayer Networks via Cross-Network Embedding
    AAAI 2024 ·

    Guojing Ren

    DBLP profile ↗ORCID search ↗
21. Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
    NeurIPS 2024 ·

    Kai Xiong

    DBLP profile ↗ORCID search ↗
22. On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey
    ACL 2024 ·

    Lin Long

    DBLP profile ↗ORCID search ↗
23. Self-Evolving GPT: A Lifelong Autonomous Experiential Learner
    ACL 2024 ·

    Jinglong Gao

    DBLP profile ↗ORCID search ↗