Lifeng Shang

Venues

Frequent coauthors

Papers

1. Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4
   ACL 2026 ·

   Chengwu Liu

   DBLP profile ↗ORCID search ↗
2. EssayBench: Evaluating Large Language Models in Multi-Genre Chinese Essay Writing
   AAAI 2026 ·

   Fan Gao

   DBLP profile ↗ORCID search ↗
3. How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
   ACL 2026 ·

   Zhexin Zhang

   DBLP profile ↗ORCID search ↗
4. Improved Policy Optimization for Mixture-of-Experts Models: Importance Sampling and Rewarding from an Expert-Centric Perspective
   ACL 2026 ·

   Yining Qian

   DBLP profile ↗ORCID search ↗
5. MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers
   ACL 2026 ·

   Linrui Ma

   DBLP profile ↗ORCID search ↗
6. Process Evaluation for Agentic Systems
   EACL 2026 ·

   Milan Gritta

   DBLP profile ↗ORCID search ↗
7. Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
   ACL 2026 ·

   Bowen Ding

   DBLP profile ↗ORCID search ↗
8. ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool learning
   AAAI 2026 ·

   Xingshan Zeng

   DBLP profile ↗ORCID search ↗
9. Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
   ICLR 2025 ·

   Yuxin Jiang

   DBLP profile ↗ORCID search ↗
10. Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
    NAACL 2025 ·

    Zezhong Wang

    DBLP profile ↗ORCID search ↗
11. Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge
    ACL 2025 ·

    Qiyuan Zhang

    DBLP profile ↗ORCID search ↗
12. DeepDiver: Adaptive Web-Search Intensity Scaling via Reinforcement Learning
    NeurIPS 2025 ·

    Wenxuan Shi

    DBLP profile ↗ORCID search ↗
13. Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
    ICML 2025 ·

    Tao Li

    DBLP profile ↗ORCID search ↗
14. Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction
    ACL 2025 ·

    Yuxin Jiang

    DBLP profile ↗ORCID search ↗
15. Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework
    ACL 2025 ·

    Kaishuai Xu

    DBLP profile ↗ORCID search ↗
16. More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression
    EMNLP 2025 ·

    Jiebin Zhang

    DBLP profile ↗ORCID search ↗
17. QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
    NeurIPS 2025 ·

    Wanlong Liu

    DBLP profile ↗ORCID search ↗
18. RevisEval: Improving LLM-as-a-Judge via Response-Adapted References
    ICLR 2025 ·

    Qiyuan Zhang

    DBLP profile ↗ORCID search ↗
19. RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models
    NeurIPS 2025 ·

    Junda Zhu

    DBLP profile ↗ORCID search ↗
20. Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
    ACL 2025 ·

    Chengwu Liu

    DBLP profile ↗ORCID search ↗
21. Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning
    ACL 2025 ·

    Erxin Yu

    DBLP profile ↗ORCID search ↗
22. Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning
    EMNLP 2025 ·

    Zezhong Wang

    DBLP profile ↗ORCID search ↗
23. Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing
    ACL 2025 ·

    Kaishuai Xu

    DBLP profile ↗ORCID search ↗
24. ToolACE: Winning the Points of LLM Function Calling
    ICLR 2025 ·

    Weiwen Liu

    DBLP profile ↗ORCID search ↗
25. ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis
    NAACL 2025 ·

    Zezhong Wang

    DBLP profile ↗ORCID search ↗
26. FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
    ACL 2024 ·

    Yuxin Jiang

    DBLP profile ↗ORCID search ↗
27. Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis
    ICLR 2024 ·

    Kai Chen

    DBLP profile ↗ORCID search ↗
28. Learning to Edit: Aligning LLMs with Knowledge Editing
    ACL 2024 ·

    Yuxin Jiang

    DBLP profile ↗ORCID search ↗
29. M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models
    ACL 2024 ·

    Wai-Chung Kwan

    DBLP profile ↗ORCID search ↗
30. MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
    EMNLP 2024 ·

    Wai-Chung Kwan

    DBLP profile ↗ORCID search ↗
31. Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios
    ACL 2024 ·

    Shijue Huang

    DBLP profile ↗ORCID search ↗
32. Preparing Lessons for Progressive Training on Language Models
    AAAI 2024 ·

    Yu Pan

    DBLP profile ↗ORCID search ↗
33. Prompt-Based Length Controlled Generation with Multiple Control Types
    ACL 2024 ·

    Renlong Jie

    DBLP profile ↗ORCID search ↗
34. ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models
    ACL 2024 ·

    Haochen Tan

    DBLP profile ↗ORCID search ↗
35. Retrieval-based Disentangled Representation Learning with Natural Language Supervision
    ICLR 2024 ·

    Jiawei Zhou

    DBLP profile ↗ORCID search ↗
36. Visually Guided Generative Text-Layout Pre-training for Document Intelligence
    NAACL 2024 ·

    Zhiming Mao

    DBLP profile ↗ORCID search ↗