In settings from fact-checking to question answering, we frequently want to know whether a collection of evidence (premises) entails a hypothesis. Existing methods primarily focus on the end-to-end discriminative version of this task, but less work has treated the generative version in which a model searches over the space of statements entailed by the premises to constructively derive the hypothesis. We propose a system for doing this kind of deductive reasoning in natural language by decomposing the task into separate steps coordinated by a search procedure, producing a tree of intermediate conclusions that faithfully reflects the system's reasoning process. Our experiments on the EntailmentBank dataset (Dalvi et al., 2021) demonstrate that the proposed system can successfully prove true statements while rejecting false ones. Moreover, it produces natural language explanations with a 17% absolute higher step validity than those produced by an end-to-end T5 model.
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
McGill University（麦吉尔大学）；Mila - Quebec AI Institute（魁北克人工智能研究所）；University of Cambridge（剑桥大学）；MBZUAI - Mohamed bin Zayed University of Artificial Intelligence（MBZUAI - 摩苏尔·本·扎耶德人工智能大学）；University of Toronto（多伦多大学）；Salesforce
Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning
Fudan University（复旦大学）；East China Normal University（华东师范大学）；Singapore Management University（新加坡管理大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Flexible Generation of Natural Language Deductions
The University of Texas at Austin（德克萨斯大学奥斯汀分校）
一个可解释的开放领域推理系统需要以透明的形式表达其推理过程。自然语言是一种有吸引力的表示方法--它既具有高度的表达性，又易于人类理解。然而，以逻辑上一致的方式操纵自然语言语句是困难的：模型必须在保持精确的同时应对含义表达方式的变化。在本文中，我们描述了ParaPattern，一种用于构建模型的方法，该模型可以从不同的自然语言输入中生成演绎推理，而无需直接的人类监督。我们训练基于BART的模型（Lewis等人，2020）以生成将特定逻辑运算应用于一个或多个前提语句的结果。至关重要的是，我们开发了一个很大程度上自动化的管道，用于从维基百科构建合适的训练样本。我们使用来自QASC的域外句子成分来评估我们的模型（Khot et al.，2020）和EntailmentBank（Dalvi et al.，2021）数据集以及有针对性的扰动集。我们的研究结果表明，我们的模型比基线系统更准确和灵活。ParaPattern在不使用任何域内训练数据的情况下，对来自EntailmentBank的“替换”操作的示例实现了85%的有效性，与为EntailmentBank微调的模型的性能相匹配。我们的方法的完整源代码是公开的。
HOLogicBench: Evaluating Higher-Order Logical Reasoning in LLMs
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）；School of Computer Science, Peking University（北京大学计算机科学学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；YiXin-AILab, YIXIN（YiXin-AILab，YIXIN）
Fine-Grained Causality Extraction From Natural Language Requirements Using Recursive Neural Tensor Networks
Qualicen GmbH（Qualicen有限公司）；Technical University of Munich（慕尼黑工业大学）；Blekinge Institute of Technology（布莱金厄理工学院）；University of Cologne（科隆大学）；fortiss GmbH（福蒂斯有限公司）
