Papers by Zhenghao Wu
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability (2026.acl-long)
Copied to clipboard
Xiao Liang, Zhong-Zhi Li, Zhenghao Lin, Eric Hanchen Jiang, Hengyuan Zhang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Yeyun Gong, Weizhu Chen
| Challenge: | Large language models have demonstrated strong reasoning capabilities through step-by-step chain-of-thought (CoT) reasoning, but their strictly sequential nature constrains test-time scalability. |
| Approach: | They propose an end-to-end reinforcement learning framework to enhance LLMs' DAC-style reasoning capacity by decomposing a problem into subproblems and solving them sequentially. |
| Outcome: | The proposed model surpasses CoT by 8.6% and 6.3% on competition-level benchmarks and is available at the [github.com/MasterVito/DAC-RL]. |
Leveraging Prefix Transfer for Multi-Intent Text Revision (2023.acl-short)
Copied to clipboard
Ruining Chong, Cunliang Kong, Liu Wu, Zhenghao Liu, Ziye Jin, Liner Yang, Yange Fan, Hanghang Fan, Erhong Yang
| Challenge: | Text revision is a necessary process to improve text quality. |
| Approach: | They propose a multi-intent text revision system that can revise texts without explicit intent annotation. |
| Outcome: | The proposed system outperforms baselines on the IteraTeR dataset and significantly improves the SARI score with more than 3% improvement. |
LenAtten: An Effective Length Controlling Unit For Text Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Fixed length summarization (FLS) requires generating summaries with a preset number of characters or words. |
| Approach: | They propose a length control unit called LenAtten to break this trade-off by generating a short and coherent summary with the target length. |
| Outcome: | The proposed model improves controllability and ROGUE scores and generalizes well. |
Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection (2026.findings-acl)
Copied to clipboard
Zhuoyang Wu, Xinze Li, Zhenghao Liu, Yukun Yan, Zhiyuan Liu, Minghe Yu, Cheng Yang, Yu Gu, Ge Yu, Maosong Sun
| Challenge: | Existing studies treat SLMs as student models and use long-form Chains-of-Thought (CoTs) as supervision signals for Supervised Fine-Tuning (SFT). Existing research focuses on distilling reasoning ability from LLMs to enhance the mathematical reasoning performance of small-scale models. |
| Approach: | They propose a framework that refines teacher CoTs through an error-aware reflection process to enable the student model to construct more tailored teacher Cots. |
| Outcome: | Experiments on multiple mathematical reasoning benchmarks show that ORION improves performance by more than 2% over all baselines. |
RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts (2025.acl-long)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) models enable Large Language Models to access external knowledge. |
| Approach: | They propose a knowledge refinement method that incorporates reranking signals to generate CoT-based summarization based on query and retrieval documents. |
| Outcome: | RankCoT generates CoT-based summarization based on query and all retrieval documents . Rank CoT incorporates a self-reflection mechanism that refines the outputs . |
Long-Chain Reasoning Distillation via Adaptive Prefix Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, especially in solving complex mathematical problems. |
| Approach: | They propose a framework that exploits teacher CoTs for distillation through adaptive prefix alignment. |
| Outcome: | The proposed framework outperforms baseline models on multiple mathematical reasoning benchmarks by over 3%. |
SafeLawBench: Towards Safe Alignment of Large Language Models (2025.findings-acl)
Copied to clipboard
Chuxue Cao, Han Zhu, Jiaming Ji, Qichao Sun, Zhenghao Zhu, Wu Yinyu, Josef Dai, Yaodong Yang, Sirui Han, Yike Guo
| Challenge: | Recent studies indicate that large language models (LLMs) may exhibit risks, including threats to the protection of private data and the generation of hallucinations. |
| Approach: | They propose to evaluate LLMs from a legal perspective using the SafeLawBench benchmark. |
| Outcome: | The proposed framework categorizes safety risks into three levels based on legal standards and includes 24,860 multi-choice questions and 1,106 open-domain question-answering tasks. |