Xinting Huang (黄昕庭)

I am a senior researcher at Tencent, working on large language model (LLM) alignment. I obtained my PhD degree from The University of Melbourne in 2022, under the supervision of Prof. Rui Zhang . Before starting my PhD, I was an undergraduate at Renmin University of China . I have interned at Microsoft Research Asia , and Bytedance AI Lab .

My current research focuses on large language models:

  • ⭐Preference alignment & Hallucination mitigation
  • Efficient training & Synthetic data

Looking for internship or collaboration? drop me an email or a message.

❗Seeking interns to work on long-form factuality alignment: solving real-world hallucinations challenges a) Open-domain; b) Free-form generations; c) General scenarios; See Lilian's nice recap of recent academic progress.

Mail: timhuangxt AT gmail.com
Tel:   1866459006x, where x = (number of "r"s in "strawberry")2

Email  /  Google Scholar  /  Twitter  

Experiences

Tencent
Senior Researcher • Feb. 2022 to Present
Large Langauge Models (LLMs) Alignment: Hallucination mitigation, RLHF, Multi-modality


Bytedance AI Lab
Research Engineer Intern • Feb. 2021 to July. 2021
Knowledge augmented dialogue system
Mentor: Hang Li

Microsoft Research Asia
Research Intern • Feb. 2017 to July. 2017
Personalized generative recommendation
Mentor: Ruihua Song
Selected Publications (full list)

(†: Corresponding author)

Preference alignment & Hallucination mitigation
Knowledge Verification to Nip Hallucination in the Bud
Fanqi Wan, Xinting Huang †, Leyang Cui, Xiaojun Quan, Wei Bi, Shuming Shi
EMNLP, 2024
🤗Huggingface Models / Github
SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving
Xueliang Zhao, Xinting Huang †, Wei Bi, Lingpeng Kong
ACL, 2024
Github
BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models
Xueliang Zhao, Xinting Huang †, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong
ACL Findings, 2024
Github / media coverage (twitter)
Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration
Fanqi Wan, Xinting Huang †, Tao Yang, Xiaojun Quan, Wei Bi, Shuming Shi
EMNLP, 2023
🤗Huggingface Models / media coverage (zh) / Github
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Tencent AI Lab NLP Group
Preprint, 2023
media coverage (zh)
Efficient training & Synthetic data
Knowledge Fusion of Large Language Models
Fanqi Wan, Xinting Huang †, Deng Cai, Xiaojun Quan, Wei Bi, Shuming Shi,
ICLR, 2024
🤗Huggingface Models / media coverage (twitter) / media coverage (zh) / Github
Pre-training Multi-party Dialogue Models with Latent Discourse Inference
Yiyang Li, Xinting Huang †, Wei Bi, Hai Zhao
ACL, 2023
Github
TeGit: Generating High-Quality Instruction-Tuning Data with Text-Grounded Task Design
Yongrui Chen, Haiyun Jiang, Xinting Huang, Shuming Shi, Guilin Qi
NAACL, 2024
🤗Huggingface Models / Github
FuseChat: Knowledge Fusion of Chat Models
Fanqi Wan, Ziyi Yang, Longguang Zhong, Xiaojun Quan, Xinting Huang, Wei Bi
Technical Report, 2024
🤗Huggingface Models / media coverage (twitter) / media coverage (zh) / Github
Dialogue systems
Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering
Shiquan Yang, Xinting Huang †, Jey Han Lau, Sarah Erfani
EMNLP Findings, 2022
Latent reasoning for low-resource question generation
Xinting Huang, Jianzhong Qi, Yu Sun, Rui Zhang
ACL Findings, 2021
Generalizable and Explainable Dialogue Generation via Explicit Action Learning
Xinting Huang, Jianzhong Qi, Yu Sun, Rui Zhang
EMNLP Findings, 2020
Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation
Xinting Huang, Jianzhong Qi, Yu Sun, Rui Zhang
ACL, 2020
MALA: Cross-domain dialogue generation with action learning
Xinting Huang, Jianzhong Qi, Yu Sun, Rui Zhang
AAAI, 2020
LLM PaaS
Inferflow: an Efficient and Highly Configurable Inference Engine for Large Language Models
Tencent AI Lab NLP Group
Technical Report, 2024
Project Homepage / Github / media coverage (weibo)
Effidit: An Assistant for Improving Writing Efficiency
Tencent AI Lab NLP Group
ACL (System Demonstrations), 2023
Project Homepage / Demo / media coverage (zh) / media coverage (en)
Education
Ph.D. Feb. 2018 - Feb. 2022
School of Computing and Information Systems, The University of Melbourne, Australia
B.S. Sep. 2013 - Jun. 2017
School of Information, Renmin University of China (RUC)
Professional Activities

Program Committee Member/Reviewer:
  • ACL Rolling Review(2022- ), ACL(2021-2023), EMNLP(2021-2023), NAACL(2021-2023)
  • AAAI(2019- ), WSDM(2020- ), NeurIPS(2021- )

  • Design and source code from Jon Barron's website