Zobrazeno 1 - 10
of 8 902
pro vyhledávání: '"Feng Shi"'
Autor:
Feng, Shi, Gerencsér, Balázs
Considering a Markov chain defined on a cycle, near-quadratic improvement of mixing is shown when only a subtle perturbation is introduced to the structure and non-reversible transition probabilities are used. More precisely, a mixing time of $O(n^{\
Externí odkaz:
http://arxiv.org/abs/2411.07125
Multimodal conversation, a crucial form of human communication, carries rich emotional content, making the exploration of the causes of emotions within it a research endeavor of significant importance. However, existing research on the causes of emot
Externí odkaz:
http://arxiv.org/abs/2411.02430
Comparison data elicited from people are fundamental to many machine learning tasks, including reinforcement learning from human feedback for large language models and estimating ranking models. They are typically subjective and not directly verifiab
Externí odkaz:
http://arxiv.org/abs/2410.23243
Autor:
Balepur, Nishant, Gu, Feng, Ravichander, Abhilasha, Feng, Shi, Boyd-Graber, Jordan, Rudinger, Rachel
Question answering (QA)-producing correct answers for input questions-is popular, but we test a reverse question answering (RQA) task: given an input answer, generate a question with that answer. Past work tests QA and RQA separately, but we test the
Externí odkaz:
http://arxiv.org/abs/2410.15512
Autor:
Wang, Ming, Liu, Yuanzhong, Liang, Xiaoyu, Huang, Yijie, Wang, Daling, Yang, Xiaocui, Shen, Sijia, Feng, Shi, Zhang, Xiaoming, Guan, Chaofeng, Zhang, Yifei
LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI experts. Existing research in prompt engineering suggests somewhat scatter
Externí odkaz:
http://arxiv.org/abs/2409.13449
Autor:
Wen, Jiaxin, Zhong, Ruiqi, Khan, Akbir, Perez, Ethan, Steinhardt, Jacob, Huang, Minlie, Bowman, Samuel R., He, He, Feng, Shi
Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this problem: to achieve higher rewards, LMs might get better at convincing
Externí odkaz:
http://arxiv.org/abs/2409.12822
Motivated by the abundance of symmetry breaking states in magic-angle twisted bilayer graphene and other two-dimensional materials, we study superconducting (SC) and charge orders in two-dimensional topological flat bands in the strong correlation re
Externí odkaz:
http://arxiv.org/abs/2408.14533
Multi-hop Question Answering (QA) necessitates complex reasoning by integrating multiple pieces of information to resolve intricate questions. However, existing QA systems encounter challenges such as outdated information, context window length limit
Externí odkaz:
http://arxiv.org/abs/2408.11875
Competitive debate is a complex task of computational argumentation. Large Language Models (LLMs) suffer from hallucinations and lack competitiveness in this field. To address these challenges, we introduce Agent for Debate (Agent4Debate), a dynamic
Externí odkaz:
http://arxiv.org/abs/2408.04472
Autor:
Zhang, Yiqun, Yang, Xiaocui, Xu, Xingle, Gao, Zeran, Huang, Yijie, Mu, Shiyi, Feng, Shi, Wang, Daling, Zhang, Yifei, Song, Kaisong, Yu, Ge
Affective Computing (AC), integrating computer science, psychology, and cognitive science knowledge, aims to enable machines to recognize, interpret, and simulate human emotions.To create more value, AC can be applied to diverse scenarios, including
Externí odkaz:
http://arxiv.org/abs/2408.04638