In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL utilize sparse or dense retrievers and derive effective performance. However, these methods do not utilize direct feedback of LLM to train the retriever and the examples selected can not necessarily improve the analogy ability of LLM. To tackle this, we propose our policy-based reinforcement learning framework for example selection (RLS), which consists of a language model (LM) selector and an LLM generator. The LM selector encodes the candidate examples into dense representations and selects the top-k examples into the demonstration for LLM. The outputs of LLM are adopted to compute the reward and policy gradient to optimize the LM selector. We conduct experiments on different datasets and significantly outperform existing example selection methods. Moreover, our approach shows advantages over supervised finetuning (SFT) models in few shot setting. Further experiments show the balance of abundance and the similarity with the test case of examples is important for ICL performance of LLM.
Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Ant Group(蚂蚁集团)
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
Tencent Inc(腾讯公司);MPI Informatics(马克斯·普朗克信息学研究所);Saarland Informatics Campus(萨尔大学信息学院);Institute of Software, University of Chinese Academy of Science(中国科学院大学软件研究所);Alibaba Group(阿里巴巴集团);IBM Research(IBM研究院)
RSMLP: A light Sampled MLP Structure for Incomplete Utterance Rewrite
Hunan University(湖南大学);College of Electrical and Information Engineering, Hunan University(湖南大学电气与信息工程学院);Greater Bay Area Institute for Innovation, Hunan University(湖南大学粤港澳大湾区创新研究院)
Fostering Natural Conversation in Large Language Models with NICO: a Natural Interactive COnversation dataset
International Digital Economy Academy(国际数字经济学院);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);University of Michigan, Ann Arbor(密歇根大学安娜堡分校);Simon Fraser University(西蒙菲莎大学)
SDR-GNN: Spectral Domain Reconstruction Graph Neural Network for Incomplete Multimodal Learning in Conversational Emotion Recognition
College of Computer and Mathematics, Central South University of Forestry and Technology(中南林业科技大学计算机与数学学院);Department of Computer Science, State University of New York(纽约州立大学计算机科学系)
Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation
Cinnamon AI(Cinnamon人工智能公司);Hung Yen University of Technology and Education(兴安技术教育大学)
本文介绍了一种用于不完整话语恢复的模型JET(\textbf{J}),它是一个基于学习标记\textbf{E}提取和\textbf{T}下一代的模型。与以往的研究只工作在提取或抽象数据集不同,我们设计了一个简单而有效的模型,适用于两种情况下的IUR。我们的设计模拟IUR的性质,从上下文中省略的令牌有助于恢复。由此,我们构造一个识别省略的标记的选择器。为了支持选择器,我们设计了两种标签创建方法(软标签和硬标签),它们可以在省略的标记没有注释数据的情况下工作。恢复是通过使用发电机与联合学习的帮助下,选择。在四个基准数据集上的提取和抽象场景中的令人满意的结果表明,我们的模型在丰富和有限的训练数据设置中都优于预训练的T5和非生成语言模型方法。\footnote{The code is available at \url{https://github.com/shumpei19/JET}}