Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models von Pawelczyk, Martin, Sun, Lillian, Qi, Zhenting, Kumar, Aounon, Lakkaraju, Himabindu

Volltext bestellen

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems von Qi, Zhenting, Zhang, Hanlin, Xing, Eric, Kakade, Sham, Lakkaraju, Himabindu

Volltext bestellen

Quantifying Generalization Complexity for Large Language Models von Qi, Zhenting, Luo, Hongyin, Huang, Xuliang, Zhao, Zhuokai, Jiang, Yibo, Fan, Xiangjun, Lakkaraju, Himabindu, Glass, James

Volltext bestellen

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers von Qi, Zhenting, Ma, Mingyuan, Xu, Jiahang, Zhang, Li Lyna, Yang, Fan, Yang, Mao

Volltext bestellen

ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples von Zhao, Yilun, Nan, Linyong, Qi, Zhenting, Zhang, Rui, Radev, Dragomir

Volltext bestellen

Weakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection Model von Qi, Zhenting, Zhu, Ruike, Fu, Zheyu, Chai, Wenhao, Kindratenko, Volodymyr

Volltext bestellen

PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching von Qi, Zhenting, Tan, Xiaoyu, Shi, Shaojie, Qu, Chao, Xu, Yinghui, Qi, Yuan

Volltext bestellen

RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations von Zhao, Yilun, Zhao, Chen, Nan, Linyong, Qi, Zhenting, Zhang, Wenlin, Tang, Xiangru, Mi, Boyu, Radev, Dragomir

Volltext bestellen

LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control von Zhao, Yilun, Qi, Zhenting, Nan, Linyong, Flores, Lorenzo Jaime Yu, Radev, Dragomir

Volltext bestellen

Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge von Du, Weihua, Lyu, Qiushi, Shan, Jiaming, Qi, Zhenting, Zhang, Hongxin, Chen, Sunli, Peng, Andi, Shu, Tianmin, Lee, Kwonjoon, Dariush, Behzad, Gan, Chuang

Volltext bestellen

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems von Zhenting Qi, Zhang, Hanlin, Xing, Eric, Kakade, Sham, Lakkaraju, Himabindu

Volltext

P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains von Han, Simeng, Yu, Aaron, Shen, Rui, Qi, Zhenting, Riddell, Martin, Zhou, Wenfei, Qiao, Yujie, Zhao, Yilun, Yavuz, Semih, Liu, Ye, Joty, Shafiq, Zhou, Yingbo, Xiong, Caiming, Radev, Dragomir, Ying, Rex, Cohan, Arman

Volltext bestellen

QTSumm: Query-Focused Summarization over Tabular Data von Zhao, Yilun, Qi, Zhenting, Nan, Linyong, Mi, Boyu, Liu, Yixin, Zou, Weijin, Han, Simeng, Chen, Ruizhe, Tang, Xiangru, Xu, Yumo, Radev, Dragomir, Cohan, Arman

Volltext bestellen

Quantifying Generalization Complexity for Large Language Models von Zhenting Qi, Luo, Hongyin, Huang, Xuliang, Zhao, Zhuokai, Jiang, Yibo, Fan, Xiangjun, Lakkaraju, Himabindu, Glass, James

Volltext

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers von Zhenting Qi, Ma, Mingyuan, Xu, Jiahang, Li Lyna Zhang, Yang, Fan, Mao, Yang

Volltext

ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples von Zhao, Yilun, Linyong Nan, Zhenting Qi, Zhang, Rui, Radev, Dragomir

Volltext

Weakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection Model von Zhenting Qi, Zhu, Ruike, Fu, Zheyu, Chai, Wenhao, Kindratenko, Volodymyr

Volltext

PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching von Zhenting Qi, Tan, Xiaoyu, Shi, Shaojie, Qu, Chao, Xu, Yinghui, Yuan Qi

Volltext

RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations von Zhao, Yilun, Chen, Zhao, Linyong Nan, Zhenting Qi, Zhang, Wenlin, Tang, Xiangru, Mi, Boyu, Radev, Dragomir

Volltext

LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control von Zhao, Yilun, Zhenting Qi, Linyong Nan, Lorenzo Jaime Yu Flores, Radev, Dragomir

Volltext