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。
Guoli Yin, Haoping Bai, Shuang Ma +21 authors
MMAU benchmark evaluates large language models' capabilities across multiple domains and essential skills using comprehensive offline tasks to enhance interpretability and reliability.
Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez +7 authors
Chain-of-thought prompting enhances large language model performance primarily in math or logic tasks by improving symbolic reasoning, but it is less beneficial in other domains and can be selectively applied to save inference costs.
Jiajun Shi, Siyuan Tao, Yuhao Wu +18 authors
S³Gym evaluates whether large language model agents can self-test, self-judge, and self-improve through interaction experience across text-based games, revealing that effective self-improvement depends on task structure and experience representation.
Dawei Li, Bohan Jiang, Liangjie Huang +10 authors
A survey of LLM-based judgment and assessment explores definitions, taxonomy, benchmarks, challenges, and future directions for the LLM-as-a-judge paradigm.
Stephen Casper, Xander Davies, Claudia Shi +29 authors
RLHF is analyzed for its limitations and flaws, with suggestions for improvement, complementation, and oversight to enhance safer AI development.
SeungHeon Doh, Keunwoo Choi, Jongpil Lee +1 authors
A large-scale pseudo music caption dataset generated using LLMs improves music captioning performance over supervised models in zero-shot and transfer-learning settings.
Xing Han Lù, Zdeněk Kasner, Siva Reddy
A benchmark and retrieval-inspired model for efficient conversational web navigation by digital agents across diverse real-world websites is introduced, highlighting challenges in generalization to unseen sites.
Weiquan Huang, Aoqi Wu, Yifan Yang +8 authors
LLM2CLIP leverages large language models to enhance CLIP's multimodal representation learning, enabling better handling of complex image captions by fine-tuning the LLM and using contrastive learning.
Jinze Bai, Shuai Bai, Yunfei Chu +45 authors
Qwen, a series of large language models, including chat and specialized coding and mathematics variants, exhibit superior performance across various tasks and outperform open-source models.
Shubham Toshniwal, Ivan Moshkov, Sean Narenthiran +3 authors
A new math instruction tuning dataset, OpenMathInstruct-1, leverages the Mixtral model to achieve competitive performance on math reasoning benchmarks using open-source LLMs.
Kumar Tanmay, Aditi Khandelwal, Utkarsh Agarwal +1 authors
A new evaluation framework connects human psychology and AI to assess the moral reasoning and development stages of large language models using a Psychometric Assessment Tool.
Jian Xie, Kai Zhang, Jiangjie Chen +5 authors
TravelPlanner is a new benchmark for evaluating the planning capabilities of language agents in complex, real-world travel planning scenarios, demonstrating that current models still struggle with information gathering and constraint management.
Sihang Li, Jin Huang, Jiaxi Zhuang +7 authors
A hybrid approach combining continual pre-training and supervised fine-tuning creates specialized LLMs for scientific literature, addressing challenges in constructing corpora and generating instructions.
Tianle Li, Ge Zhang, Quy Duc Do +2 authors
LIConBench evaluates long-context LLMs on extreme-label classification tasks with sequences up to 50K tokens, highlighting performance dips beyond 20K tokens and favoring of recent labels.
Haoran Xu, Amr Sharaf, Yunmo Chen +5 authors
Contrastive Preference Optimization (CPO) enhances moderate-sized LLMs in machine translation, enabling them to match or exceed state-of-the-art model performance.
Cheng-Yu Hsieh, Si-An Chen, Chun-Liang Li +5 authors
LLMs can effectively use tool documentation instead of demonstrations to perform complex tasks, achieving performance comparable or superior to few-shot learning on both vision and language benchmarks.
Sondos Mahmoud Bsharat, Aidar Myrzakhan, Zhiqiang Shen
Guiding principles streamline querying and prompting of large language models, enhancing understanding and effectiveness across different scales.
Hanoona Rasheed, Muhammad Maaz, Sahal Shaji +7 authors
GLaMM is a multimodal model that generates visually grounded language responses with object segmentation masks from both text and optional visual prompts.
Jie Huang, Xinyun Chen, Swaroop Mishra +4 authors
This paper evaluates the intrinsic self-correction capabilities of Large Language Models and identifies limitations in their ability to improve responses without external feedback.
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.
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