Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala +1 authors
Language models produce incorrect statements due to training and evaluation procedures that reward guessing over acknowledging uncertainty, leading to a need for socio-technical changes in benchmark scoring.
Zuhao Yang, Sudong Wang, Kaichen Zhang +7 authors
LongVT, an end-to-end framework, enhances long video reasoning by interleaving global and local analysis using multimodal tools, outperforming existing methods on challenging benchmarks.
LASA Team, Weiwen Xu, Hou Pong Chan +16 authors
A medical-specialized multimodal large language model, Lingshu, is introduced with enhanced data curation and reinforcement learning to address limitations in medical applications.
Zijian Li, Xin Guan, Bo Zhang +9 authors
WebWeaver, a dual-agent framework, addresses open-ended deep research challenges by integrating adaptive planning and focused synthesis to produce high-quality, reliable reports.
Le Xue, Manli Shu, Anas Awadalla +24 authors
xGen-MM, an extension of Salesforce's xGen initiative, provides a framework for developing Large Multimodal Models with pre-trained, instruction-tuned, and safety-tuned variants.
Zhongxing Xu, Zhonghua Wang, Zhe Qian +10 authors
Latent Entropy-Aware Decoding (LEAD) enhances multimodal large reasoning models by using entropy-aware reasoning mode switching and prior-guided visual anchor injection to reduce hallucinations.
Ding Chen, Simin Niu, Kehang Li +6 authors
HaluMem, a benchmark for evaluating memory hallucinations in AI systems, identifies and analyzes hallucinations across memory extraction, updating, and question answering stages using large-scale human-AI interaction datasets.
Yuanzhi Li, Sébastien Bubeck, Ronen Eldan +3 authors
A new 1.3 billion parameter Transformer-based language model, phi-1.5, demonstrates comparable performance to much larger models on common sense reasoning and complex tasks despite the absence of web data.
Min Shi, Fuxiao Liu, Shihao Wang +12 authors
Mixture of vision encoders and resolutions in multimodal large language models improves performance through concatenation of visual tokens and a Pre-Alignment mechanism, leading to superior results on benchmarks.
Gagan Bhatia, El Moatez Billah Nagoudi, Hasan Cavusoglu +1 authors
FinTral, a multimodal LLM enhanced through domain-specific pretraining, instruction fine-tuning, and RLAIF, outperforms ChatGPT-3.5 and GPT-4 in financial analysis tasks with exceptional zero-shot performance.
Zunhai Su, Hengyuan Zhang, Wei Wu +17 authors
Transformers face challenges from Attention Sink phenomenon where excessive attention focuses on uninformative tokens, impacting interpretability and performance, necessitating comprehensive research survey addressing fundamental usage, mechanistic understanding, and strategic mitigation approaches.
Zhenran Xu, Longyue Wang, Jifang Wang +7 authors
FilmAgent, a multi-agent collaborative framework based on LLMs, automates film production processes including scriptwriting, cinematography, and actor positioning, outperforming other models in human evaluations.
Wenxuan Zhang, Hou Pong Chan, Yiran Zhao +9 authors
SeaLLMs 3 is a large language model optimized for Southeast Asian languages, offering state-of-the-art performance in various tasks while addressing safety and cultural considerations.
Baixiang Huang, Canyu Chen, Xiongxiao Xu +2 authors
HalluEditBench benchmarks knowledge editing methods in correcting hallucinations in Large Language Models (LLMs) using a comprehensive dataset and evaluation framework.
Hadas Orgad, Michael Toker, Zorik Gekhman +4 authors
LLMs internally encode detailed truthfulness information about their outputs, which can be used to detect and predict errors but shows variability across datasets and does not always align with the final output.
Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu +4 authors
The Chain-of-Verification method reduces hallucinations in language models by having them draft, plan verification questions, answer independently, and then generate a final verified response.
Yung-Sung Chuang, Yujia Xie, Hongyin Luo +3 authors
A decoding strategy that contrasts logits from different transformer layers reduces hallucinations in large language models without external knowledge or fine-tuning.
Zhen Zeng, William Watson, Nicole Cho +4 authors
FlowMind uses Large Language Models with a generic prompt recipe to generate automatic workflows, addressing spontaneous tasks and ensuring data integrity, and it is evaluated using a new financial dataset NCEN-QA.
Katherine Tian, Eric Mitchell, Huaxiu Yao +2 authors
Fine-tuning language models using automatically generated factuality preference rankings improves their factual accuracy without human labeling.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号