Papers by Mingjie Zhou

8 papers
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.
MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning (2025.findings-acl)

Copied to clipboard

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%.
ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to enhance code generation performance include integrating compiler feedback.
Approach: They propose a method that integrates compiler feedback to improve one-off code generation performance.
Outcome: The proposed method improves one-off code generation performance on three benchmarks and can be applied to other domains that focus on final results and require long reasoning paths.
Probability-Consistent Preference Optimization for Enhanced LLM Reasoning (2025.findings-acl)

Copied to clipboard

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.
AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks (2023.findings-acl)

Copied to clipboard

Challenge: Tabular data analysis is performed everyday across various domains.
Approach: They propose to use a dataset of 467k tables with supervision labels for four types of field metadata.
Outcome: The proposed framework improves the understanding capability of tabular models by incorporating distribution and knowledge information.
LeLoRA: Learnable Low-Rank Adaptation of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to fine-tuning large language models (LLMs) rely on manually specified and fixed hyperparameters, resulting in suboptimal performance and low parameter efficiency.
Approach: They propose a framework that allows for dynamically learned adaptive adaptation strategies to be used to fine-tune large language models.
Outcome: The proposed framework outperforms baselines in adapting large language models.
Alignment with Fill-In-the-Middle for Enhancing Code Generation (2025.emnlp-main)

Copied to clipboard

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.
Why Are We Moral? An LLM-based Agent Simulation Approach to the Study of Moral Evolution (2026.acl-long)

Copied to clipboard

Challenge: Existing models of moral evolution must abstract away cognitive processes . et al. (2017): evolution of morality presents a puzzle: natural selection favors selfish .
Approach: They propose an LLM-based agent simulation framework that manipulates cognitive factors to understand moral evolution.
Outcome: The proposed model exploits cognitive realism to explore moral evolution in a hunter-gatherer society.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations