Papers by Weikang Zhou
MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs (2024.acl-long)
Copied to clipboard
| Challenge: | Existing models have demonstrated outstanding capabilities in mathematical reasoning, but there is a performance gap between open-source models and closed-source ones. |
| Approach: | They propose a method for generating diverse and reliable math problems by leveraging the ground-truth solutions of the seed data. |
| Outcome: | The proposed model outperforms open-source models across five representative mathematical reasoning datasets. |
Order Doesn’t Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Logical reasoning is essential for large language models (LLMs) to ensure accurate and coherent inferences. |
| Approach: | They propose an order-centric data augmentation framework based on commutativity in logical reasoning that randomly shuffles independent premises to introduce condition order augmentation. |
| Outcome: | The proposed framework improves LLMs’ reasoning performance and adaptability to diverse logical structures. |
MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning (2025.findings-acl)
Copied to clipboard
Ke Wang, Junting Pan, Linda Wei, Aojun Zhou, Weikang Shi, Zimu Lu, Han Xiao, Yunqiao Yang, Houxing Ren, Mingjie Zhan, Hongsheng Li
| Challenge: | Large Language Models (LMMs) struggle with simple tasks such as geometry, e.g., arithmetic, and reasoning. |
| Approach: | They propose to leverage code as supervision for cross-modal alignment . they propose to use FigCodifier and ImgCode-8.6M to synthesize novel mathematical figures . |
| Outcome: | The proposed model surpasses GPT-4o and Claude 3.5 Sonnet in the geometry problem-solving subset of MathVista, achieving improvements of 8.9% and 9.2%. |
Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model (2023.findings-acl)
Copied to clipboard
Xiao Wang, Weikang Zhou, Qi Zhang, Jie Zhou, SongYang Gao, Junzhe Wang, Menghan Zhang, Xiang Gao, Yun Wen Chen, Tao Gui
| Challenge: | Pretrained language models have achieved remarkable success in various natural language processing tasks. |
| Approach: | They propose to use end-task knowledge to select a tiny subset of pretraining corpus to influence performance. |
| Outcome: | The proposed model outperforms pretrained models on eight datasets covering four domains with 0.45% of the data and a three-orders-of-magnitude lower computational cost. |
Multi-Programming Language Sandbox for LLMs (2025.acl-demo)
Copied to clipboard
Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang
| Challenge: | MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs). |
| Approach: | They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models. |
| Outcome: | The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs). |
Probability-Consistent Preference Optimization for Enhanced LLM Reasoning (2025.findings-acl)
Copied to clipboard
Yunqiao Yang, Houxing Ren, Zimu Lu, Ke Wang, Weikang Shi, Aojun Zhou, Junting Pan, Mingjie Zhan, Hongsheng Li
| Challenge: | Recent advances in preference optimization have demonstrated significant potential for improving mathematical reasoning capabilities in large language models. |
| Approach: | They propose a framework that establishes two quantitative metrics for preference selection: surface-level answer correctness and intrinsic token-level probability consistency. |
| Outcome: | The proposed framework outperforms existing outcome-only criterion approaches across a diverse range of LLMs and benchmarks. |
Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks treat memory as a static append-only archive . Existing systems focus on passive accumulation, resulting in a 'passive accumulation' of memory. |
| Approach: | They propose a framework for experience-driven agent evolution that integrates procedural memory with contextual information to create a high-quality experience pool. |
| Outcome: | Experiments on BFCL-V3 and AppWorld show that ReMe outperforms memoryless Qwen3-8B. |
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning (2026.acl-long)
Copied to clipboard
Weikang Shi, Aldrich Yu, Rongyao Fang, Houxing Ren, Ke Wang, Aojun Zhou, Changyao Tian, Xinyu Fu, Yuxuan Hu, Zimu Lu, Linjiang Huang, Si Liu, Rui Liu, Hongsheng Li
| Challenge: | Existing approaches to visual chain-of-thought are limited by external tools or fail to generate high-fidelity diagrams. |
| Approach: | They propose a framework to enable large multimodal models with VCoT capabilities . they pre-train a model on a 15.2M-pair corpus and teach it how to leverage visual aids . |
| Outcome: | The proposed framework unlocks complex, human-like visual reasoning in large language models . it pre-trains the model on a 15.2M-pair corpus and fine-tunes it on MathCanvas-Instruct . |
LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding (2025.emnlp-main)
Copied to clipboard
Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zheng, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li
| Challenge: | Recent advances in Large Language Models have opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS). |
| Approach: | They propose a framework that leverages LLMs for cross-domain neural architecture optimization without extensive domain-specific tuning. |
| Outcome: | The proposed framework achieves competitive performance in both in-domain and out-of-domain tasks. |
Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | In real-world scenarios, user instructions often contain soft constraints, which are semantically related and cannot be rule-based verified, posing challenges for large language models. |
| Approach: | They propose a pipeline to construct datasets with high-quality outputs for instructions containing soft constraints automatically and use Direct Preference Optimization (DPO) as the training method. |
| Outcome: | The proposed model improves the LLMs' soft constraint following ability by using direct preference optimization (DPO) and constraint quantity. |
Alignment with Fill-In-the-Middle for Enhancing Code Generation (2025.emnlp-main)
Copied to clipboard
Houxing Ren, Zimu Lu, Weikang Shi, Haotian Hou, Yunqiao Yang, Ke Wang, Aojun Zhou, Junting Pan, Mingjie Zhan, Hongsheng Li
| Challenge: | Existing methods for generating test cases with limited training data are not reliable and may be counterproductive. |
| Approach: | They propose a method that splits code snippets into smaller, granular blocks, creating more diverse DPO pairs from the same test cases. |
| Outcome: | The proposed approach shows significant improvements in code generation tasks on benchmark datasets such as HumanEval (+), MBPP (+), and APPS. |
Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to enhance credibility and verifiability of large language models (LLMs) mainly focus on passage-level or paragraph-level references or citations, which fall short in verifikatability. |
| Approach: | They propose a method that provides sentence-level citations in LLM-generated responses. |
| Outcome: | The proposed method achieves 90% accuracy in long-form question-answering tasks. |
Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models struggle to follow multi-constraint instructions in real-world applications. |
| Approach: | They propose to quantify the difficulty distribution of constraints by a novel Difficulty Distribution Index (CDDI) they find that LLMs are more performant when presented with constraints in a “hard-to-easy” order. |
| Outcome: | The proposed model is more performant when presented with constraints in a “hard-to-easy” order, compared with existing models with different architectures and sizes of parameters. |