Zobrazeno 1 - 10
of 103
pro vyhledávání: '"DU Xinya"'
The rapid advancements in large language models (LLMs) have demonstrated their potential to accelerate scientific discovery, particularly in automating the process of research ideation. LLM-based systems have shown promise in generating hypotheses an
Externí odkaz:
http://arxiv.org/abs/2412.14626
FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning
Hallucinations in large language models (LLMs) pose significant challenges in tasks requiring complex multi-step reasoning, such as mathematical problem-solving. Existing approaches primarily detect the presence of hallucinations but lack a nuanced u
Externí odkaz:
http://arxiv.org/abs/2410.06304
As an essential task in information extraction (IE), Event-Event Causal Relation Extraction (ECRE) aims to identify and classify the causal relationships between event mentions in natural language texts. However, existing research on ECRE has highlig
Externí odkaz:
http://arxiv.org/abs/2410.04752
The rapid development of Large Vision-Language Models (LVLMs) often comes with widespread hallucination issues, making cost-effective and comprehensive assessments increasingly vital. Current approaches mainly rely on costly annotations and are not c
Externí odkaz:
http://arxiv.org/abs/2409.13612
Autor:
Jing, Liqiang, Huang, Zhehui, Wang, Xiaoyang, Yao, Wenlin, Yu, Wenhao, Ma, Kaixin, Zhang, Hongming, Du, Xinya, Yu, Dong
Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) have demonstrated impressive language/vision reasoning abilities, igniting the recent trend of building agents for targeted applications such as shopping assistants or AI software
Externí odkaz:
http://arxiv.org/abs/2409.07703
Machine learning research, crucial for technological advancements and innovation, often faces significant challenges due to its inherent complexity, slow pace of experimentation, and the necessity for specialized expertise. Motivated by this, we pres
Externí odkaz:
http://arxiv.org/abs/2408.14033
To evaluate Large Language Models (LLMs) for question answering (QA), traditional methods typically focus on assessing single-turn responses to given questions. However, this approach doesn't capture the dynamic nature of human-AI interactions, where
Externí odkaz:
http://arxiv.org/abs/2408.13545
Autor:
Gu, Jing, Fang, Yuwei, Skorokhodov, Ivan, Wonka, Peter, Du, Xinya, Tulyakov, Sergey, Wang, Xin Eric
Video editing is a cornerstone of digital media, from entertainment and education to professional communication. However, previous methods often overlook the necessity of comprehensively understanding both global and local contexts, leading to inaccu
Externí odkaz:
http://arxiv.org/abs/2406.12831
Autor:
Jing, Liqiang, Du, Xinya
Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination problems, i
Externí odkaz:
http://arxiv.org/abs/2404.05046
Autor:
Li, Ruosen, Du, Xinya
Neural models, including large language models (LLMs), achieve superior performance on multi-hop question-answering. To elicit reasoning capabilities from LLMs, recent works propose using the chain-of-thought (CoT) mechanism to generate both the reas
Externí odkaz:
http://arxiv.org/abs/2311.03734