Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Hu, Xiangkun"'
Autor:
Liu, Tengxiao, Guo, Qipeng, Hu, Xiangkun, Jiayang, Cheng, Zhang, Yue, Qiu, Xipeng, Zhang, Zheng
Trained on vast corpora of human language, language models demonstrate emergent human-like reasoning abilities. Yet they are still far from true intelligence, which opens up intriguing opportunities to explore the parallels of humans and model behavi
Externí odkaz:
http://arxiv.org/abs/2411.01855
Autor:
Ru, Dongyu, Qiu, Lin, Hu, Xiangkun, Zhang, Tianhang, Shi, Peng, Chang, Shuaichen, Jiayang, Cheng, Wang, Cunxiang, Sun, Shichao, Li, Huanyu, Zhang, Zizhao, Wang, Binjie, Jiang, Jiarong, He, Tong, Wang, Zhiguo, Liu, Pengfei, Zhang, Yue, Zhang, Zheng
Despite Retrieval-Augmented Generation (RAG) showing promising capability in leveraging external knowledge, a comprehensive evaluation of RAG systems is still challenging due to the modular nature of RAG, evaluation of long-form responses and reliabi
Externí odkaz:
http://arxiv.org/abs/2408.08067
Large language models in the past have typically relied on some form of reinforcement learning with human feedback (RLHF) to better align model responses with human preferences. However, because of oft-observed instabilities when implementing these R
Externí odkaz:
http://arxiv.org/abs/2407.09072
Cross-document event coreference resolution (CDECR) involves clustering event mentions across multiple documents that refer to the same real-world events. Existing approaches utilize fine-tuning of small language models (SLMs) like BERT to address th
Externí odkaz:
http://arxiv.org/abs/2406.02148
Autor:
Hu, Xiangkun, Ru, Dongyu, Qiu, Lin, Guo, Qipeng, Zhang, Tianhang, Xu, Yang, Luo, Yun, Liu, Pengfei, Zhang, Yue, Zhang, Zheng
Large Language Models (LLMs) have shown impressive capabilities but also a concerning tendency to hallucinate. This paper presents RefChecker, a framework that introduces claim-triplets to represent claims in LLM responses, aiming to detect fine-grai
Externí odkaz:
http://arxiv.org/abs/2405.14486
Autor:
Wang, Cunxiang, Ning, Ruoxi, Pan, Boqi, Wu, Tonghui, Guo, Qipeng, Deng, Cheng, Bao, Guangsheng, Hu, Xiangkun, Zhang, Zheng, Wang, Qian, Zhang, Yue
The rapid advancement of Large Language Models (LLMs) has introduced a new frontier in natural language processing, particularly in understanding and processing long-context information. However, the evaluation of these models' long-context abilities
Externí odkaz:
http://arxiv.org/abs/2403.12766
Autor:
Liu, Tengxiao, Guo, Qipeng, Yang, Yuqing, Hu, Xiangkun, Zhang, Yue, Qiu, Xipeng, Zhang, Zheng
As large language models (LLMs) have shown effectiveness with different prompting methods, such as Chain of Thought, Program of Thought, we find that these methods have formed a great complementarity to each other on math reasoning tasks. In this wor
Externí odkaz:
http://arxiv.org/abs/2310.14628
Recent works have introduced Abstract Meaning Representation (AMR) for Document-level Event Argument Extraction (Doc-level EAE), since AMR provides a useful interpretation of complex semantic structures and helps to capture long-distance dependency.
Externí odkaz:
http://arxiv.org/abs/2305.19162
Autor:
Wang, Cunxiang, Xu, Zhikun, Guo, Qipeng, Hu, Xiangkun, Bai, Xuefeng, Zhang, Zheng, Zhang, Yue
The Open-Domain Question Answering (ODQA) task involves retrieving and subsequently generating answers from fine-grained relevant passages within a database. Current systems leverage Pretrained Language Models (PLMs) to model the relationship between
Externí odkaz:
http://arxiv.org/abs/2305.17050
Autor:
Wang, Cunxiang, Cheng, Sirui, Guo, Qipeng, Yue, Yuanhao, Ding, Bowen, Xu, Zhikun, Wang, Yidong, Hu, Xiangkun, Zhang, Zheng, Zhang, Yue
This study focuses on the evaluation of the Open Question Answering (Open-QA) task, which can directly estimate the factuality of large language models (LLMs). Current automatic evaluation methods have shown limitations, indicating that human evaluat
Externí odkaz:
http://arxiv.org/abs/2305.12421