Tian Liang - THU | personal description

I work at Tencent AI Lab as a research scientist now in Shenzhen.

I graduated from Wuhan University (2017/09 - 2021/06) with a bachelor’s degree and from the Intelligent Interaction Group, SIGS @ Tsinghua University (2021/09 - 2024/06) with a master’s degree, advised by Prof. Yujiu Yang.

Research

I am generally interested in natural language processing and machine learning. Current interests include:

  • Self-Play Post-training Paradigm
  • Effective model architecture
  • Efficient training and inference

Publications

* denotes co-first authors, $^\dagger$ denotes corresponding author/main advisor

Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
Tian Liang*, Zhiwei He*, Wenxiang Jiao*, Xing Wang$^\dagger$, Yan Wang, Rui Wang, Yujiu Yang$^\dagger$, Zhaopeng Tu, Shuming Shi
EMNLP 2024. [arxiv] [code] [bib] [Citations: 173 🎉🎉]

Addressing Entity Translation Problem via Translation Difficulty and Context Diversity
Tian Liang, Xing Wang$^\dagger$, Mingming Yang, Yujiu Yang$^\dagger$, Shuming Shi, Zhaopeng Tu
ACL 2024. [paper] [code] [bib]

Exploring Human-Like Translation Strategy with Large Language Models
Zhiwei He*, Tian Liang*, Wenxiang Jiao, Zhuosheng Zhang, Yujiu Yang, Rui Wang$^\dagger$, Zhaopeng Tu$^\dagger$, Shuming Shi, Xing Wang
TACL 2023. [arxiv] [code] [bib]

CriticBench: Benchmarking LLMs for Critique-Correct Reasoning
Zicheng Lin*, Zhibin Gou*, Tian Liang, Ruilin Luo, Haowei Liu, Yujiu Yang$^\dagger$
ACL 2024. [arxiv] [code] [bib]

ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback
Wenxiang Jiao*, Jen-tse Huang, Wenxuan Wang, Zhiwei He, Tian Liang, Xing Wang, Shuming Shi, Zhaopeng Tu
EMNLP 2023. [arxiv] [code] [bib]

Leveraging word guessing games to assess the intelligence of large language models
Tian Liang, Zhiwei He, Jen-tes Huang, Wenxuan Wang, Wenxiang Jiao$^\dagger$, Rui Wang, Yujiu Yang$^\dagger$, Zhaopeng Tu, Shuming Shi, Xing Wang$^\dagger$
ARXIV 2023. [arxiv] [bib]

How Far Are We on the Decision-Making of LLMs? Evaluating LLMs’ Gaming Ability in Multi-Agent Environments
Jen-tse Huang, Eric John Li, Man Ho Lam, Tian Liang, Wenxuan Wang, Youliang Yuan, Wenxiang Jiao$^\dagger$, Xing Wang, Zhaopeng Tu, Michael R. Lyu
ARXIV 2024. [arxiv] [bib]

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Jiahao Xu, Tian Liang, Pinjia He, Zhaopeng Tu
ARXIV 2024. [arxiv] [code] [bib]

Competition

* denotes co-first authors, $^\dagger$ denotes corresponding author/main advisor

Acronym extraction with hybrid strategies
SDU@ AAAI-22, Rank 2nd.
Siheng Li*, Cheng Yang*, Tian Liang*, Xinyu Zhu, Chengze Yu, Yujiu Yang$^\dagger$
AAAI 2022 Workshop. [paper] [code] [bib]

Multilingual Acronym Disambiguation with Multi-choice Classification
SDU@ AAAI-22, Rank 4th.
Xinyu Zhu*, Chengze Yu*, Siheng Li, Tian Liang, Cheng Yang, Yujiu Yang$^\dagger$
AAAI 2022 Workshop. [paper] [code] [bib]