Papers by Mingfeng Xue

7 papers
Rationales for Answers to Simple Math Word Problems Confuse Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Recent studies show that large language models have advanced mathematical problem-solving abilities in grade school math word problems.
Approach: They propose to combine fine-tuning and prompt-based methods to improve performance . they propose to use a hybrid algorithm to fine- tune LLMs on specific tasks .
Outcome: The proposed methods improve performance on the proposed reasoning process evaluation benchmarks.
Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing unsupervised paraphrase generation methods require large-scale, manually annotated paraphrase datasets, which are labor-intensive to build.
Approach: They propose a self-supervised pseudo-data construction method that generates diverse pseudo-paraphrases in distinct surface structures for a given sentence.
Outcome: The proposed method generates diverse pseudo-paraphrases in distinct surface structures for a given sentence.
START: Self-taught Reasoner with Tools (2025.emnlp-main)

Copied to clipboard

Challenge: Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex reasoning through long chain-of-thought, yet they struggle with precise computations and algorithmic operations.
Approach: They propose a training-free approach that activates LRMs’ latent tool-use capabilities through artificial hints and a framework that enables models to learn effective tool utilization through diverse hint patterns and rejection-based data synthesis.
Outcome: Experiments show that START significantly improves state-of-the-art LRMs across challenging benchmarks, including competition-level mathematics (AMC23: 95.0%, AIME24: 75.6%) and graduate-level science questions (GPQA: 64.6%).
Controllable LLM Reasoning via Sparse Autoencoder-Based Steering (2026.acl-long)

Copied to clipboard

Challenge: Existing methods struggle to control fine-grained reasoning strategies due to conceptual entanglement in LRMs’ hidden states.
Approach: They propose to decompose strategy-entangled hidden states into a disentangled feature space by using Sparse Autoencoders to identify the few strategy-specific features from the vast pool of SAE features.
Outcome: The proposed method outperforms existing methods by 15% in control effectiveness.
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition (2024.acl-long)

Copied to clipboard

Challenge: supervised fine-tuning (SFT) is a technique used to enhance multiple abilities in large language models.
Approach: They propose to study the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning.
Outcome: The proposed model improves math reasoning and code generation with increasing data amount . the proposed model size and SFT strategies can be used to learn multiple skills with different scaling patterns.
Tailor: A Soft-Prompt-Based Approach to Attribute-Based Controlled Text Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing work focuses on generating sentences satisfying pre-specified attributes such as topic and sentiment, yet suffers from increases in storage and inference time.
Approach: They propose a method that uses a pre-trained continuous vector to generate a fixed pre-trainable language model to satisfy a specified attribute.
Outcome: The proposed model can achieve improvements on eleven attribute-specific generation tasks with 0.08% extra training parameters.
Dynamic Voting for Efficient Reasoning in Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Multi-path voting methods generate multiple reasoning paths for each problem, causing factual errors and illusion generation.
Approach: They propose a multi-path voting technique that effectively reduces the number of reasoning paths during multi-path voting while preserving accuracies.
Outcome: The proposed method outperforms Self-consistency using 24.7% of the number of paths on the LetterConcat task.

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