Fei Mi (糜飞)

Principle Research Scientist, Huawei Noah’s Ark Lab,

Shenzhen, China

[Google Scholar]

Email: mifei2 [at] huawei.com

General

Fei Mi is a Principle research scientist at Huawei Noah’s Ark Lab, Working on Huawei PanGu Model Alignment. He obtained his Ph.D. degree in Computer Science from The Swiss Federal Institute of Technology Lausanne (EPFL) in 2021, supervised by Prof. Boi Faltings. Prior to that, he obtained his MPhill degree from Hong Kong University of Science and Technology (HKUST) under the supervision of Prof. Dit-Yan Yeung. Prior to that, he obtained his Bachelar degree from a join program from Sun-Yat-Sen University and HKUST.

Research Interests

LLM Alignment

News

Interns are welcome: we are hiring research interns! If you are interested in LLM Alignment, feel free to contact me!!

• Three papers are accepted by ACL 2024.
• Two papers are accepted by NAACL 2024.
• One paper is accepted by ICLR 2024.
• Four papers are accepted by EMNLP 2023 Main and Findings.
• Serving as AC of ACL 2023; Six papers are accepted by ACL 2023 Main and Findings.
• Two papers are accepted by EMNLP 2022 Main and three papers accepted by EMNLP Findings 2022
• 第一版盘古Bot (PanGu-Bot)中文对话模型已发布!! 详情链接
• Two papers are accepted by ACL 2022 one paper accepted by NAACL 2022!!

Publications

Pre-prints

• Data Management For Large Language Models: A Survey
• Aligning large language models with human: A survey
• SELF: Language-driven self-evolution for large language model
• Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment
• YODA: Teacher-Student Progressive Learning for Language Models
• PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model.

Conference

2024 ———–>

• FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models ACL 2024
• Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization ACL 2024
• Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation ACL 2024
• Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis ICLR 2024
• REGA: Role Prompting Guided Multi-Domain Adaptation for Large Language Models NAACL 2024
• Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting NAACL 2024

2023 ———–>

• ReSee: Responding through Seeing Fine-grained Visual Knowledge in Open-domain Dialogue. EMNLP 2023 Main

• Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs. EMNLP 2023 Findings

• Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogues. EMNLP 2023 Findings

• Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment. EMNLP 2023 Findings

• A Synthetic Data Generation Framework for Grounded Dialogues. ACL 2023 Main

• [Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models](https://aclanthology.org/2023.acl-long.608/. ACL 2023 Main

• DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering. ACL 2023 Main

• MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions. ACL 2023 Main

• One Cannot Stand for Everyone! Leveraging Multiple User Simulators to train Task-oriented Dialogue Systems. ACL 2023 Main

• Towards Fewer Hallucinations in Knowledge-Grounded Dialogue Generation via Augmentative and Contrastive Knowledge-Dialogue. ACL 2023 Short

• Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables. Bin Sun, Yitong Li, Fei Mi, Weichao Wang, Yiwei Li, Kan Li. AAAI 2023

• KPT: Keyword-guided Pre-training for Grounded Dialog Generation. Qi Zhu, Fei Mi, Zheng Zhang, Yasheng Wang, Yitong Li, Xin Jiang, Qun Liu, Xiaoyan Zhu, Minlie Huang. AAAI 2023

2022 ———–>

• AEG: Argumentative Essay Generation via A Dual-Decoder Model with Content Planning. Jianzhu Bao, Yasheng Wang, Yitong Li, Fei Mi and Ruifeng Xu. EMNLP Main 2022.

• COLD: A Benchmark for Chinese Offensive Language Detection. Jiawen Deng, Jingyan ZHOU, Hao Sun, Chujie Zheng, Fei Mi, Helen Meng and Minlie Huang. EMNLP Main 2022.

• Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation. Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Fei Mi, Yasheng Wang, Lifeng Shang, Hongning Wang and Minlie Huang. Findings of EMNLP 2022.

• Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks. Jingyan Zhou, Jiawen Deng, Fei Mi, Yitong Li, Yasheng Wang, Minlie Huang, Xin Jiang, Qun Liu, Helen Meng. Findings of EMNLP 2022.

• Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder. Bin Sun, Shaoxiong Feng, Yiwei Li, Weichao Wang, Fei Mi, Yitong Li and Kan Li. Findings of EMNLP 2022.

• Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation. Yihe Wang, Yitong Li, Yasheng Wang, Fei Mi, Pingyi Zhou, Xin Wang, Jin Liu, Xin Jiang, Qun Liu. COLING 2022

• LMTurk: Few-Shot Learners as Crowdsourcing Workers. Mengjie Zhao, Fei Mi, Yasheng Wang, Minglei Li, Xin Jiang, Qun Liu, Hinrich Schütze. NAACL Findings 2022

• Continual Prompt Tuning for Dialog State Tracking. Qi Zhu, Bing Li, Fei Mi, Minlie Huang, Xiaoyan Zhu. ACL Main 2022

• Compilable Neural Code Generation with Compiler Feedback. Xin Wang, Yasheng Wang, Yao Wan, Fei Mi, Yitong Li, Pingyi Zhou, jin liu, hao wu, Xin Jiang, Qun Liu. ACL Findings 2022

• SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling. Fengyu Cai, Wanhao Zhou, Fei Mi, Boi Faltings. ICASSP 2022

• CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems. Fei Mi, Yitong Li, Yasheng Wang. AAAI 2022 — Oral (5%)

Earlier ———–>

• Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems. Fei Mi, Wanhao Zhou, Fengyu Cai, Lingjing Kong, Minlie Huang, Boi Faltings. EMNLP 2021 — Oral (5%)

• Continual Learning for Natural Language Generation in Task-oriented Dialog Systems. Fei Mi, Liangwei Chen, Mengjie Zhao, Minlie Huang, Boi Faltings. Findings of EMNLP 2020.

• Masking as an Efficient Alternative to Finetuning for Pretrained Language Models. Mengjie Zhao, Tao Lin, Fei Mi, Martin Jaggi, Hinrich Schütze. EMNLP, 2020.

• ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation. Fei Mi, Xiaoyu Lin, Boi Faltings. The ACM Conference on Recommender Systems (RecSys), 2020. (short paper) — The best short paper award

• Memory Augmented Neural Model for Incremental Session-based Recommendation. Fei Mi, Boi Faltings. IJCAI, 2020.

• Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems. Fei Mi, Minlie Huang, Jiyong Zhang, Boi Faltings. IJCAI, 2019.

• Adaptive Sequential Recommendation for Discussion Forums on MOOCs using Context Trees. Fei Mi, Boi Faltings. International Conference on Educational Data Mining (EDM), 2017.

• Probabilistic Graphical Models for Boosting Cardinal and Ordinal Peer Grading in MOOCs. Fei Mi, Dit-Yan Yeung. AAAI, 2015.

Workshop

• UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues. Xinyan Zhao, Bin He, Yasheng Wang, Yitong Li, Fei Mi, Yajiao Liu, Xin Jiang, Qun Liu, Huanhuan Chen. ACL Doc2Dial Workshop

• Generalized Class Incremental Learning, Fei Mi, Lingjing Kong, Tao Lin, Kaichen Yu, Boi Faltings. CVPR Workshop on “Continual Learning in Computer Vision” (CLVISION), 2020.

• Personalization in Goal-oriented Dialog, Chaitanya K. Joshi, Fei Mi, Boi Faltings NIPS Workshop on “Conversational AI”, 2017.

• Temporal Models for Predicting Student Dropout in Massive Open Online Courses, Fei Mi, Dit-Yan Yeung. IEEE International Conference on Data Mining Workshop (ICDMW), 2015.