Výsledky vyhledávání

Report

Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs

Autor: Zhou, Xin, Nie, Ping, Guo, Yiwen, Wei, Haojie, Zhang, Zhanqiu, Minervini, Pasquale, Ma, Ruotian, Gui, Tao, Zhang, Qi, Huang, Xuanjing

Retrieval-Augmented Generation (RAG) significantly improved the ability of Large Language Models (LLMs) to solve knowledge-intensive tasks. While existing research seeks to enhance RAG performance by retrieving higher-quality documents or designing R

Externí odkaz: http://arxiv.org/abs/2410.15438

Zobrazit plný text záznamu

Report

The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models

Autor: Hong, Giwon, Gema, Aryo Pradipta, Saxena, Rohit, Du, Xiaotang, Nie, Ping, Zhao, Yu, Perez-Beltrachini, Laura, Ryabinin, Max, He, Xuanli, Fourrier, Clémentine, Minervini, Pasquale

Large Language Models (LLMs) have transformed the Natural Language Processing (NLP) landscape with their remarkable ability to understand and generate human-like text. However, these models are prone to ``hallucinations'' -- outputs that do not align

Externí odkaz: http://arxiv.org/abs/2404.05904

Zobrazit plný text záznamu

Report

Beyond Prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations

Autor: Fei, Yu, Nie, Ping, Meng, Zhao, Wattenhofer, Roger, Sachan, Mrinmaya

Recent work has demonstrated that pre-trained language models (PLMs) are zero-shot learners. However, most existing zero-shot methods involve heavy human engineering or complicated self-training pipelines, hindering their application to new situation

Externí odkaz: http://arxiv.org/abs/2210.16637

Zobrazit plný text záznamu

Report

Anticipating the Unseen Discrepancy for Vision and Language Navigation

Autor: Lu, Yujie, Zhang, Huiliang, Nie, Ping, Feng, Weixi, Xu, Wenda, Wang, Xin Eric, Wang, William Yang

Vision-Language Navigation requires the agent to follow natural language instructions to reach a specific target. The large discrepancy between seen and unseen environments makes it challenging for the agent to generalize well. Previous studies propo

Externí odkaz: http://arxiv.org/abs/2209.04725

Zobrazit plný text záznamu