Large language models (LLMs) have emerged as versatile tools in various daily applications. However, they are fraught with issues that undermine their utility and trustworthiness. These include the incorporation of erroneous references (citation), the generation of hallucinated information (correctness), and the inclusion of superfluous or omission of crucial details (fluency). To ameliorate these concerns, this study makes several key contributions. First, we build a dataset to train a critic model capable of evaluating the citation, correctness, and fluency of responses generated by LLMs in QA systems. Second, we propose an automated feedback mechanism that leverages the critic model to offer real-time feedback on heterogeneous aspects of generated text. Third, we introduce a feedback learning loop that uses this critic model to iteratively improve the performance of the LLM responsible for response generation. Experimental results demonstrate the efficacy of our approach, showing substantial improvements in citation and fluency metrics for ChatGPT, including a 4% precision increase in citation and an approximately 8% enhancement in the MAUVE metric for fluency, while maintaining high levels of correctness.
Large Language Models Meet User Interfaces: The Case of Provisioning Feedback
School of Electrical Engineering and Computer Science(电气工程与计算机科学学院);The University of Queensland(昆士兰大学);Institute for Teaching and Learning Innovation(教学创新研究所);Centre for Learning Analytics(学习分析中心);Faculty of Information Technology(信息技术学院);Monash University(莫纳什大学);School of Computer Science(计算机科学学院);University of Auckland(奥克兰大学)
Improving In-Context Learning with Prediction Feedback for Sentiment Analysis
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies(广东省新型安全智能技术重点实验室);SIAT, Chinese Academy of Science(中国科学院深圳先进技术研究院);The 30th Research Institute of China Electronics Technology Group Corporation(中国电子科技集团公司第三十研究所);Harbin Institute of Technology(哈尔滨工业大学);Peng Cheng Laboratory, Shenzhen(鹏城实验室(深圳))
Training Language Models with Language Feedback at Scale
New York University(纽约大学);FAR AI;University of the Basque Country UPV/EHU(巴斯克大学);University of Sussex(萨塞克斯大学);Genentech(基因泰克公司);CIFAR LMB(加拿大高级研究院分子生物学与遗传学实验室);Anthropic(Anthropic公司)
My Words Imply Your Opinion: Reader Agent-based Propagation Enhancement for Personalized Implicit Emotion Analysis
School of Computer and Information Technology, Shanxi University, China(山西大学计算机与信息学院);Institute of Automation, Chinese Academy of Science, China(中国科学院自动化研究所);Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, China(教育部计算智能与中文信息处理重点实验室);Joint Laboratory of Tourism Big Data in Shanxi Province, China(山西省旅游大数据联合实验室)
Collaborative Filtering with Topic and Social Latent Factors Incorporating Implicit Feedback
Nanjing University(南京大学);Nanjing University of Science and Technology(南京理工大学);Nanjing University of Posts and Telecommunications(南京邮电大学);Florida International University(佛罗里达国际大学)
Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering
South China University of Technology(华南理工大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Tencent AI Lab(腾讯人工智能实验室);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))