Mingfeng Xue

7 papers · 2023–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (22) 🐣 Hot Topic Early Bird

Venues

ACL (4) EMNLP (3)

Top co-authors

Dayiheng Liu (7) jun xie (3) Baosong Yang (3) Yidan Zhang (3) Wenqiang Lei (3) Jiancheng Lv (2) Chengpeng Li (2) Dezhong Peng (2) Binyuan Hui (1) Jie Fu (1)

Research topics

Machine Learning (5) Natural Language Processing (5) Learning Types · Machine Learning (5) Artificial Intelligence (4) Core AI (4) Resources & Methods (3) Deep Learning (2) Applications (2) Generation (2) Learning Types · Deep Learning (2) Core Methods (1)

Keywords

large language model (3) large reasoning model (2) catastrophic forgetting (1) multi-task learning (1) mathematical reasoning (1) text generation (1) paraphrase generation (1) feature disentanglement (1) tool use (1) supervised fine-tuning (1) parameter-efficient tuning (1) sparse autoencoder (1) soft prompt (1) reasoning model (1) reasoning evaluation (1) discrete representation (1) prompt tuning (1) continuous representation (1) rejection sampling (1) data composition (1)

Papers

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering ACL 2026 START: Self-taught Reasoner with Tools EMNLP 2025 How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition ACL 2024 Rationales for Answers to Simple Math Word Problems Confuse Large Language Models ACL 2024 Dynamic Voting for Efficient Reasoning in Large Language Models EMNLP 2023 Tailor: A Soft-Prompt-Based Approach to Attribute-Based Controlled Text Generation ACL 2023 Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation EMNLP 2023