Bowen Yu

Venues

Frequent coauthors

Papers

1. On the Editability of Delta Parameters in Post-Trained Models
   ACL 2026 ·

   Qiaoyu Tang

   DBLP profile ↗ORCID search ↗
2. Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
   ACL 2026 ·

   Binghai Wang

   DBLP profile ↗ORCID search ↗
3. PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice
   ACL 2026 ·

   Yuzhen Shi

   DBLP profile ↗ORCID search ↗
4. Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
   NeurIPS 2025 ·

   Shenzhi Wang

   DBLP profile ↗ORCID search ↗
5. Efficient Long Context Fine-tuning with Chunk Flow
   ICML 2025 ·

   Xiulong Yuan

   DBLP profile ↗ORCID search ↗
6. LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability
   EMNLP 2025 ·

   Zikai Xiao

   DBLP profile ↗ORCID search ↗
7. MARGE: Improving Math Reasoning with Guided Exploration
   ICML 2025 ·

   Jingyue Gao

   DBLP profile ↗ORCID search ↗
8. P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs
   EMNLP 2025 ·

   Yidan Zhang

   DBLP profile ↗ORCID search ↗
9. ProcessBench: Identifying Process Errors in Mathematical Reasoning
   ACL 2025 ·

   Chujie Zheng

   DBLP profile ↗ORCID search ↗
10. RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing
    EMNLP 2025 ·

    Hao Xiang

    DBLP profile ↗ORCID search ↗
11. Rethinking Data Selection at Scale: Random Selection is Almost All You Need
    EMNLP 2025 ·

    Tingyu Xia

    DBLP profile ↗ORCID search ↗
12. START: Self-taught Reasoner with Tools
    EMNLP 2025 ·

    Chengpeng Li

    DBLP profile ↗ORCID search ↗
13. Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models
    ACL 2025 ·

    Hao Xiang

    DBLP profile ↗ORCID search ↗
14. Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
    ICLR 2025 ·

    Guanting Dong

    DBLP profile ↗ORCID search ↗
15. The Lessons of Developing Process Reward Models in Mathematical Reasoning
    ACL 2025 ·

    Zhenru Zhang

    DBLP profile ↗ORCID search ↗
16. Transferable Post-training via Inverse Value Learning
    NAACL 2025 ·

    Xinyu Lu

    DBLP profile ↗ORCID search ↗
17. Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
    ICML 2024 ·

    Le Yu

    DBLP profile ↗ORCID search ↗
18. Language Models can Evaluate Themselves via Probability Discrepancy
    ACL 2024 ·

    Tingyu Xia

    DBLP profile ↗ORCID search ↗
19. Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment
    ACL 2024 ·

    Keming Lu

    DBLP profile ↗ORCID search ↗
20. Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model
    EMNLP 2024 ·

    Chenhan Yuan

    DBLP profile ↗ORCID search ↗
21. Preference Ranking Optimization for Human Alignment
    AAAI 2024 ·

    Feifan Song

    DBLP profile ↗ORCID search ↗
22. Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
    NeurIPS 2024 ·

    Qiaoyu Tang

    DBLP profile ↗ORCID search ↗
23. SoFA: Shielded On-the-fly Alignment via Priority Rule Following
    ACL 2024 ·

    Xinyu Lu

    DBLP profile ↗ORCID search ↗
24. TRUE-UIE: Two Universal Relations Unify Information Extraction Tasks
    NAACL 2024 ·

    Yucheng Wang

    DBLP profile ↗ORCID search ↗