Large language models (LLMs) such as GPT-4 have exhibited remarkable performance in a variety of tasks, but this strong performance often comes with the high expense of using paid API services. In this paper, we are motivated to study building an LLM cascade to save the cost of using LLMs, particularly for performing reasoning (e.g., mathematical, causal) tasks. Our cascade pipeline follows the intuition that simpler questions can be addressed by a weaker but more affordable LLM, whereas only the challenging questions necessitate the stronger and more expensive LLM. To realize this decision-making, we consider the "answer consistency" of the weaker LLM as a signal of the question difficulty and propose several methods for the answer sampling and consistency checking, including one leveraging a mixture of two thought representations (i.e., Chain-of-Thought and Program-of-Thought). Through experiments on six reasoning benchmark datasets, with GPT-3.5-turbo and GPT-4 being the weaker and stronger LLMs, respectively, we demonstrate that our proposed LLM cascades can achieve performance comparable to using solely the stronger LLM but require only 40% of its cost.
Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
Fudan University（复旦大学）；Alibaba Group Holding Limited（阿里巴巴集团控股有限公司）；Future Living Lab of Alibaba（阿里巴巴未来生活实验室）；University of Southern California（南加州大学）；Shanghai Innovation Institute（上海创新研究院）
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Alibaba Group（阿里巴巴集团）；Computational Bioscience Research Center, KAUST（阿卜杜拉国王科技大学计算生物科学研究中心）
An automatically discovered chain-of-thought prompt generalizes to novel models and datasets
Medical University of Vienna（维也纳医科大学）；Johannes Kepler University Linz（林茨约翰内斯·开普勒大学）；KTH Royal Institute of Technology（KTH皇家理工学院）；Humboldt University Berlin（柏林洪堡大学）
Listening or Reading? Evaluating Speech Awareness in Chain-of-Thought Speech-to-Text Translation
Barcelona Supercomputing Center, Spain（巴塞罗那超级计算中心）；Universitat Politècnica de Catalunya, Spain（加泰罗尼亚理工大学）；DFKI GmbH, Saarland Informatics Campus, Saarbrücken, Germany（DFKI GmbH萨尔兰信息技术校区）
Machine Learning Research, Morgan Stanley, New York, NY（机器学习研究部，摩根士丹利，纽约，纽约）；School of Electrical and Computer Engineering, Cornell University, Ithaca, NY（电气与计算机工程学院，康奈尔大学，伊萨卡，纽约）
Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns
School of Computer Science, Peking University（北京大学计算机科学系）；Meituan（美团）；State Key Laboratory of Multimedia Information Processing, Peking University（北京大学多媒体信息处理国家重点实验室）
Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
`Who would have thought of that!': A Hierarchical Topic Model for Extraction of Sarcasm-prevalent Topics and Sarcasm Detection
Indian Institute of Technology Bombay（印度理工学院孟买分校）；Monash University（莫纳什大学）；IITB-Monash Research Academy（印度理工学院孟买分校-莫纳什研究学院）；IIT-BHU (Varanasi)（印度理工学院贝纳拉斯印度教大学分校（瓦拉纳西））
