Publications
Most recent publications on Google Scholar.
* denotes co-first authors
AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
Chang Ma*, Junlei Zhang*, Zhihao Zhu*, Cheng Yang*, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, Lingpeng Kong, Junxian He
NeurIPS 2024 (Datasets and Benchmarks Track). [arxiv] [github]
Oral
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
Yuxuan Tong, Xiwen Zhang, Rui Wang, Ruidong Wu, Junxian He
NeurIPS 2024. [arxiv] [github]
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs
Zhiyuan Hu, Chumin Liu, Xidong Feng, Yilun Zhao, See-Kiong Ng, Anh Tuan Luu, Junxian He, Pang Wei Koh, Bryan Hooi
NeurIPS 2024. [arxiv]
On the Universal Truthfulness Hyperplane Inside LLMs
Junteng Liu, Shiqi Chen, Yu Cheng, Junxian He
EMNLP 2024.
Belief Revision: The Adaptability of Large Language Models Reasoning
Bryan Wilie, Samuel Cahyawijaya, Etsuko Ishii, Junxian He , Pascale Fung
EMNLP 2024.
Compression Represents Intelligence Linearly
Yuzhen Huang*, Jinghan Zhang*, Zifei Shan, Junxian He
COLM 2024. [arxiv] [code]
Prompt Optimization via Adversarial In-Context Learning
Xuan Long Do*, Yiran Zhao*, Hannah Brown*, Yuxi Xie, James Xu Zhao, Nancy F. Chen, Kenji Kawaguchi, Michael Qizhe Xie, Junxian He
ACL 2024. [arxiv]
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
Shiqi Chen*, Miao Xiong*, Junteng Liu, Zhengxuan Wu, Teng Xiao, Siyang Gao, Junxian He
ICML 2024. [arxiv] [code]
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
Wei Liu*, Weihao Zeng*, Keqing He, Yong Jiang, Junxian He
ICLR 2024. [arxiv] [github]
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
Miao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, Bryan Hooi
ICLR 2024. [arxiv]
K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization
Cheng Deng, Tianhang Zhang, Zhongmou He, Yi Xu, Qiyuan Chen, Yuanyuan Shi, Luoyi Fu, Weinan Zhang, Xinbing Wang, Chenghu Zhou, Zhouhan Lin, Junxian He
WSDM 2024. [arxiv] [github]
Composing Parameter-Efficient Modules with Arithmetic Operations
Jinghan Zhang, Shiqi Chen, Junteng Liu, Junxian He
NeurIPS 2023. [arxiv] [code]
Decomposition Enhances Reasoning via Self-Evaluation Guided Decoding
Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, Xu Zhao, Min-Yen Kan, Junxian He, Qizhe Xie
NeurIPS 2023. [arxiv] [code]
C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
Yuzhen Huang*, Yuzhuo Bai*, Zhihao Zhu, Junlei Zhang, Jinghan Zhang, Tangjun Su, Junteng Liu, Chuancheng Lv, Yikai Zhang, Jiayi Lei, Yao Fu, Maosong Sun, Junxian He
NeurIPS 2023 (Datasets and Benchmarks track). [arxiv] [github] [website] [dataset]
FELM: Benchmarking Factuality Evaluation of Large Language Models
Shiqi Chen, Yiran Zhao, Jinghan Zhang, I-Chun Chern, Siyang Gao, Pengfei Liu, Junxian He
NeurIPS 2023 (Datasets and Benchmarks track). [arxiv] [github] [website] [dataset]
Contrastive Learning of Sentence Embeddings from Scratch
Junlei Zhang, Zhenzhong Lan, Junxian He
EMNLP 2023. [arxiv] [code]
Simple Temporal Adaptation to Changing Label Sets: Hashtag Prediction via Dense KNN
Fatemehsadat Mireshghallah, Nikolai Vogler, Junxian He, Omar Florez, Ahmed El-Kishky, Taylor Berg-Kirkpatrick
EMNLP 2023. [arxiv]
Automatic Model Selection with Large Language Models for Reasoning
Xu Zhao, Yuxi Xie, Kenji Kawaguchi, Junxian He, Qizhe Xie
EMNLP 2023 Findings. [arxiv] [code]
Mega: Moving Average Equipped Gated Attention
Xuezhe Ma*, Chunting Zhou*, Xiang Kong, Junxian He, Liangke Gui, Graham Neubig, Jonathan May, Luke Zettlemoyer
ICLR 2023. [arxiv]
CTRLsum: Towards Generic Controllable Text Summarization
Junxian He, Wojciech Kryściński, Bryan McCann, Nazneen Rajani, Caiming Xiong
EMNLP 2022. [arxiv] [code] [huggingface demo] [streamlit demo]
Prompt Consistency for Zero-Shot Task Generalization
Chunting Zhou*, Junxian He*, Xuezhe Ma, Taylor Berg-Kirkpatrick, Graham Neubig
EMNLP 2022 Findings. [arxiv]
Towards a Unified View of Parameter-Efficient Transfer Learning
Junxian He*, Chunting Zhou*, Xuezhe Ma, Taylor Berg-Kirkpatrick, Graham Neubig
ICLR 2022. [OpenReview] [arxiv] [code]
Spotlight
Capturing Structural Locality in Non-parametric Language Models
Frank F. Xu, Junxian He, Graham Neubig, Vincent Josua Hellendoorn
ICLR 2022. [arxiv]
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
Uri Alon, Frank F. Xu, Junxian He, Sudipta Sengupta, Dan Roth, Graham Neubig
ICML 2022. [arxiv] [code]
Efficient Nearest Neighbor Language Models
Junxian He, Graham Neubig, Taylor Berg-Kirkpatrick
EMNLP 2021. [arxiv] [code]
The Source-Target Domain Mismatch Problem in Machine Translation
Jiajun Shen, Peng-Jen Chen, Matthew Le, Junxian He, Jiatao Gu, Myle Ott, Michael Auli, Marc’Aurelio Ranzato
EACL 2021. [arxiv]
Dependency Induction Through the Lens of Visual Perception
Ruisi Su, Shruti Rijhwani, Hao Zhu, Junxian He, Xinyu Wang, Yonatan Bisk, Graham Neubig
CoNLL 2021. [arxiv] [code]
Learning Sparse Protoypes for Text Generation
Junxian He, Taylor Berg-Kirkpatrick, Graham Neubig
NeurIPS 2020. [arxiv] [code]
Revisiting Self-Training for Neural Sequence Generation
Junxian He*, Jiatao Gu*, Jiajun Shen, Marc’Aurelio Ranzato
ICLR 2020. [arxiv] [code]
A Probabilistic Formulation of Unsupervised Text Style Transfer
Junxian He*, Xinyi Wang*, Graham Neubig, Taylor Berg-Kirkpatrick
ICLR 2020. [arxiv] [code]
Spotlight
On the Sentence Embeddings from Pre-trained Language Models
Bohan Li, Hao Zhou, Junxian He, Mingxuan Wang, Yiming Yang, Lei Li
EMNLP 2020. [arxiv] [code]
A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text
Bohan Li*, Junxian He*, Graham Neubig, Taylor Berg-Kirkpatrick, Yiming Yang
EMNLP 2019 (short paper). [arxiv] [code]
Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections
Junxian He, Zhisong Zhang, Taylor Berg-Kirkpatrick, Graham Neubig
ACL 2019. [arxiv] [code]
Texar: A modularized, versatile, and extensible toolkit for text generation
Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wangrong Zhu, Devendra Singh Sachan, Eric P. Xing
ACL 2019 (demo paper). Best demo paper nomination. [arxiv] [GitHub]
Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
Junxian He, Daniel Spokoyny, Graham Neubig, Taylor Berg-Kirkpatrick
ICLR 2019. [arxiv] [code]
Unsupervised Learning of Syntactic Structure with Invertible Neural Projections
Junxian He, Graham Neubig, Taylor Berg-Kirkpatrick
EMNLP 2018. [arxiv] [code]
StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing
Pengcheng Yin, Chunting Zhou, Junxian He, Graham Neubig
ACL 2018. [arxiv]
Efficient Correlated Topic Modeling with Topic Embedding
Junxian He*, Zhiting Hu*, Taylor Berg-Kirkpatrick, Ying Huang, Eric Xing
KDD 2017. [arxiv]
Text Network Exploration via Heterogeneous Web of Topics
Junxian He, Ying Huang, Changfeng Liu, Jiaming Shen, Yuting Jia, Xinbing Wang
ICDM 2016 WorkShop. [arxiv] [demo]