Xiongwei Han


2025

pdf bib
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
Teng Wang | Wing Yin Yu | Zhenqi He | Zehua Liu | HaileiGong HaileiGong | Han Wu | Xiongwei Han | Wei Shi | Ruifeng She | Fangzhou Zhu | Tao Zhong
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

LLMs exhibit advanced reasoning capabilities, offering the potential to transform natural language questions into mathematical models. However, existing open-source datasets in operations research domain lack detailed annotations of the modeling process, such as variable definitions, focusing solely on objective values, which hinders reinforcement learning applications. To address this, we release the StructuredOR dataset, annotated with comprehensive labels that capture the complete mathematical modeling process. We further propose BPP-Search, an algorithm that integrates reinforcement learning into a tree-of-thought structure using Beam search, a Process reward model, and a pairwise Preference algorithm. This approach enables efficient exploration of tree structures, avoiding exhaustive search while improving accuracy. Extensive experiments on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets show that BPP-Search significantly outperforms state-of-the-art methods. In tree-based reasoning, BPP-Search excels in accuracy and efficiency, enabling faster retrieval of correct solutions. The StructuredOR dataset is available on Huggingface https://huggingface.co/datasets/LLM4OR/StructuredOR and GitHub https://github.com/LLM4OR/StructuredOR.

pdf bib
Large Language Models are good multi-lingual learners : When LLMs meet cross-lingual prompts
Teng Wang | Zhenqi He | Wing-Yin Yu | Xiaojin Fu | Xiongwei Han
Proceedings of the 31st International Conference on Computational Linguistics

With the advent of Large Language Models (LLMs), generating rule-based data for real-world applications has become more accessible. Due to the inherent ambiguity of natural language and the complexity of rule sets, especially in long contexts, LLMs often struggle to follow all specified rules, frequently omitting at least one. To enhance the reasoning and understanding of LLMs on long and complex contexts, we propose a novel prompting strategy Multi-Lingual Prompt, namely MLPrompt, which automatically translates the error-prone rule that an LLM struggles to follow into another language, thus drawing greater attention to it. Experimental results on public datasets across various tasks have shown MLPrompt can outperform state-of-the-art prompting methods such as Chain of Thought, Tree of Thought, and Self-Consistency. Additionally, we introduce a framework integrating MLPrompt with an auto-checking mechanism for structured data generation, with a specific case study in text-to-MIP instances. Further, we extend the proposed framework for text-to-SQL to demonstrate its generation ability towards structured data synthesis.

pdf bib
Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
Shuqi Liu | Han Wu | Bowei He | Xiongwei Han | Mingxuan Yuan | Linqi Song
Findings of the Association for Computational Linguistics: ACL 2025

Recent advances in large language models have led to numerous task-specialized fine-tuned variants, creating a need for efficient model merging techniques that preserve specialized capabilities while avoiding costly retraining. While existing task vector-based merging methods show promise, they typically apply uniform coefficients across all parameters, overlooking varying parameter importance both within and across tasks. We present Sens-Merging, a sensitivity-guided coefficient adjustment method that enhances existing model merging techniques by operating at both task-specific and cross-task levels. Our method analyzes parameter sensitivity within individual tasks and evaluates cross-task transferability to determine optimal merging coefficients. Extensive experiments on Mistral 7B and LLaMA2 7B/13B models demonstrate that Sens-Merging significantly improves performance across general knowledge, mathematical reasoning, and code generation tasks. Notably, when combined with existing merging techniques, our method enables merged models to outperform specialized fine-tuned models, particularly in code generation tasks. Our findings reveal important trade-offs between task-specific and cross-task scalings, providing insights for future model merging strategies.

2024

pdf bib
Towards Human-aligned Evaluation for Linear Programming Word Problems
Linzi Xing | Xinglu Wang | Yuxi Feng | Zhenan Fan | Jing Xiong | Zhijiang Guo | Xiaojin Fu | Rindra Ramamonjison | Mahdi Mostajabdaveh | Xiongwei Han | Zirui Zhou | Yong Zhang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Math Word Problem (MWP) is a crucial NLP task aimed at providing solutions for given mathematical descriptions. A notable sub-category of MWP is the Linear Programming Word Problem (LPWP), which holds significant relevance in real-world decision-making and operations research. While the recent rise of generative large language models (LLMs) has brought more advanced solutions to LPWPs, existing evaluation methodologies for this task still diverge from human judgment and face challenges in recognizing mathematically equivalent answers. In this paper, we introduce a novel evaluation metric rooted in graph edit distance, featuring benefits such as permutation invariance and more accurate program equivalence identification. Human evaluations empirically validate the superior efficacy of our proposed metric when particularly assessing LLM-based solutions for LPWP.

2023

pdf bib
LaTeX2Solver: a Hierarchical Semantic Parsing of LaTeX Document into Code for an Assistive Optimization Modeling Application
Rindra Ramamonjison | Timothy Yu | Linzi Xing | Mahdi Mostajabdaveh | Xiaorui Li | Xiaojin Fu | Xiongwei Han | Yuanzhe Chen | Ren Li | Kun Mao | Yong Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)

We demonstrate an interactive system to help operations research (OR) practitioners convert the mathematical formulation of optimization problems from TeX document format into the solver modeling language. In practice, a manual translation is cumbersome and time-consuming. Moreover, it requires an in-depth understanding of the problem description and a technical expertise to produce the modeling code. Thus, our proposed system TeX2Solver helps partially automate this conversion and help the users build optimization models more efficiently. In this paper, we describe its interface and the components of the hierarchical parsing system. A video demo walk-through is available online at http://bit.ly/3kuOm3x