Sub-Character Tokenization for Chinese Pretrained Language Models von Si, Chenglei, Zhang, Zhengyan, Chen, Yingfa, Qi, Fanchao, Wang, Xiaozhi, Liu, Zhiyuan, Wang, Yasheng, Liu, Qun, Sun, Maosong

Volltext

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers von Si, Chenglei, Yang, Diyi, Hashimoto, Tatsunori

Volltext bestellen

What's in a Name? Answer Equivalence For Open-Domain Question Answering von Si, Chenglei, Zhao, Chen, Boyd-Graber, Jordan

Volltext bestellen

Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering von Si, Chenglei, Zhang, Yanzhe, Li, Ryan, Yang, Zhengyuan, Liu, Ruibo, Yang, Diyi

Volltext bestellen

Re-Examining Calibration: The Case of Question Answering von Si, Chenglei, Zhao, Chen, Min, Sewon, Boyd-Graber, Jordan

Volltext bestellen

Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong von Si, Chenglei, Goyal, Navita, Wu, Sherry Tongshuang, Zhao, Chen, Feng, Shi, DauméIII, Hal, Boyd-Graber, Jordan

Volltext bestellen

Getting MoRE out of Mixture of Language Model Reasoning Experts von Si, Chenglei, Shi, Weijia, Zhao, Chen, Zettlemoyer, Luke, Boyd-Graber, Jordan

Volltext bestellen

Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations von Si, Chenglei, Friedman, Dan, Joshi, Nitish, Feng, Shi, Chen, Danqi, He, He

Volltext bestellen

READIN: A Chinese Multi-Task Benchmark with Realistic and Diverse Input Noises von Si, Chenglei, Zhang, Zhengyan, Chen, Yingfa, Wang, Xiaozhi, Liu, Zhiyuan, Sun, Maosong

Volltext bestellen

Prompting GPT-3 To Be Reliable von Si, Chenglei, Gan, Zhe, Yang, Zhengyuan, Wang, Shuohang, Wang, Jianfeng, Boyd-Graber, Jordan, Wang, Lijuan

Volltext bestellen

Best Practices and Lessons Learned on Synthetic Data von Liu, Ruibo, Wei, Jerry, Liu, Fangyu, Si, Chenglei, Zhang, Yanzhe, Rao, Jinmeng, Zheng, Steven, Peng, Daiyi, Yang, Diyi, Zhou, Denny, Dai, Andrew M

Volltext bestellen

Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition von Schulhoff, Sander, Pinto, Jeremy, Khan, Anaum, Bouchard, Louis-François, Si, Chenglei, Anati, Svetlina, Tagliabue, Valen, Kost, Anson Liu, Carnahan, Christopher, Boyd-Graber, Jordan

Volltext bestellen

What does BERT Learn from Multiple-Choice Reading Comprehension Datasets? von Si, Chenglei, Wang, Shuohang, Kan, Min-Yen, Jiang, Jing

Volltext bestellen

Adversarial Training for Machine Reading Comprehension with Virtual Embeddings von Yang, Ziqing, Cui, Yiming, Si, Chenglei, Che, Wanxiang, Liu, Ting, Wang, Shijin, Hu, Guoping

Volltext

What's in a Name? Answer Equivalence For Open-Domain Question Answering von Si, Chenglei, Chen, Zhao, Boyd-Graber, Jordan

Volltext

Configurable Foundation Models: Building LLMs from a Modular Perspective von Xiao, Chaojun, Zhang, Zhengyan, Song, Chenyang, Jiang, Dazhi, Yao, Feng, Han, Xu, Wang, Xiaozhi, Wang, Shuo, Huang, Yufei, Lin, Guanyu, Chen, Yingfa, Zhao, Weilin, Tu, Yuge, Zhong, Zexuan, Zhang, Ao, Si, Chenglei, Moo, Khai Hao, Zhao, Chenyang, Chen, Huimin, Lin, Yankai, Liu, Zhiyuan, Shang, Jingbo, Sun, Maosong

Volltext bestellen

Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning von Si, Chenglei, Zhang, Zhengyan, Qi, Fanchao, Liu, Zhiyuan, Wang, Yasheng, Liu, Qun, Sun, Maosong

Volltext bestellen

Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering von Si, Chenglei, Zhang, Yanzhe, Li, Ryan, Yang, Zhengyuan, Liu, Ruibo, Yang, Diyi

Volltext

Towards Bidirectional Human-AI Alignment: A Systematic Review for Clarifications, Framework, and Future Directions von Shen, Hua, Knearem, Tiffany, Ghosh, Reshmi, Alkiek, Kenan, Krishna, Kundan, Liu, Yachuan, Ma, Ziqiao, Petridis, Savvas, Peng, Yi-Hao, Qiwei, Li, Rakshit, Sushrita, Si, Chenglei, Xie, Yutong, Bigham, Jeffrey P, Bentley, Frank, Chai, Joyce, Lipton, Zachary, Mei, Qiaozhu, Mihalcea, Rada, Terry, Michael, Yang, Diyi, Morris, Meredith Ringel, Resnick, Paul, Jurgens, David

Volltext bestellen

CharBERT: Character-aware Pre-trained Language Model von Ma, Wentao, Cui, Yiming, Si, Chenglei, Liu, Ting, Wang, Shijin, Hu, Guoping

Volltext