Present language understanding methods have demonstrated extraordinary ability of recognizing patterns in texts via machine learning. However, existing methods indiscriminately use the recognized patterns in the testing phase that is inherently different from us humans who have counterfactual thinking, e.g., to scrutinize for the hard testing samples. Inspired by this, we propose a Counterfactual Reasoning Model, which mimics the counterfactual thinking by learning from few counterfactual samples. In particular, we devise a generation module to generate representative counterfactual samples for each factual sample, and a retrospective module to retrospect the model prediction by comparing the counterfactual and factual samples. Extensive experiments on sentiment analysis (SA) and natural language inference (NLI) validate the effectiveness of our method.
University of California, Los Angeles（加州大学洛杉矶分校）；Microsoft Cognitive Services Research（微软认知服务研究院）；University of Notre Dame（圣母大学）
Answering open-domain questions requires world knowledge about in-context entities. As pre-trained Language Models (LMs) lack the power to store all required knowledge, external knowledge sources, such as knowledge graphs, are often used to augment LMs. In this work, we propose knOwledge REasOning empowered Language Model (OREO-LM), which consists of a novel Knowledge Interaction Layer that can be flexibly plugged into existing Transformer-based LMs to interact with a differentiable Knowledge Graph Reasoning module collaboratively. In this way, LM guides KG to walk towards the desired answer, …
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Counterfactual reasoning requires predicting how alternative events, contrary to what actually happened, might have resulted in different outcomes. Despite being considered a necessary component of AI-complete systems, few resources have been developed for evaluating counterfactual reasoning in narratives. In this paper, we propose Counterfactual Story Rewriting: given an original story and an intervening counterfactual event, the task is to minimally revise the story to make it compatible with the given counterfactual event. Solving this task will require deep understanding of causal narrativ…
Multi-hop QA requires reasoning over multiple supporting facts to answer the question. However, the existing QA models always rely on shortcuts, e.g., providing the true answer by only one fact, rather than multi-hop reasoning, which is referred as $\textit{disconnected reasoning}$ problem. To alleviate this issue, we propose a novel counterfactual multihop QA, a causal-effect approach that enables to reduce the disconnected reasoning. It builds upon explicitly modeling of causality: 1) the direct causal effects of disconnected reasoning and 2) the causal effect of true multi-hop reasoning fro…
GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability
National Engineering Research Center for Big Data Technology and System（大数据技术与系统国家工程研究中心）；System Lab, Cluster（系统实验室，集群）；Grid Computing Lab, School of Computer Science（网格计算实验室，计算机科学学院）；Huazhong University of Science and Technology（华中科技大学）；School of Computer Science（计算机科学学院）；Microsoft Research Asia, Beijing 100190, China（微软亚洲研究院，北京100190，中国）
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；The University of Sydney（悉尼大学）；Shanghai AI Laboratory（上海人工智能实验室）；Nanyang Technological University（南洋理工大学）
R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
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）；Beijing Normal University（北京师范大学）
ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院 Gallagher 分校）；Baidu Inc., Beijing, China（百度公司，北京，中国）；Carnegie Mellon University（卡内基梅隆大学）
MC-GPT: Empowering Vision-and-Language Navigation with Memory Map and Reasoning Chains
School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区智能系统工程学院）；School of Computer Science and Engineering（计算机科学与工程学院）
针对基于LLM的VLN方法记忆构建不足、策略单一的问题，本文提出MC-GPT，通过拓扑记忆地图、Navigation Chain of Thoughts及集成流水线增强导航与推理可解释性。
In this paper, we describe an approach for modelling causal reasoning in natural language by detecting counterfactuals in text using multi-head self-attention weights. We use pre-trained transformer models to extract contextual embeddings and self-attention weights from the text. We show the use of convolutional layers to extract task-specific features from these self-attention weights. Further, we describe a fine-tuning approach with a common base model for knowledge sharing between the two closely related sub-tasks for counterfactual detection. We analyze and compare the performance of vario…
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Microsoft Corporation（微软公司）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
WizardMath 通过 RLEIF 方法在不依赖外部 Python 工具的情况下提升大语言模型的数学推理能力，在 GSM8k 和 MATH 基准上超越多个顶级开源及商用模型。
Institute for Applied Informatics at Leipzig University (InfAI)（莱比锡大学应用信息学研究所（InfAI））
We introduce the CRASS (counterfactual reasoning assessment) data set and benchmark utilizing questionized counterfactual conditionals as a novel and powerful tool to evaluate large language models. We present the data set design and benchmark that supports scoring against a crowd-validated human baseline. We test six state-of-the-art models against our benchmark. Our results show that it poses a valid challenge for these models and opens up considerable room for their improvement.
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Stanford University（斯坦福大学）
Abductive and counterfactual reasoning, core abilities of everyday human cognition, require reasoning about what might have happened at time t, while conditioning on multiple contexts from the relative past and future. However, simultaneous incorporation of past and future contexts using generative language models (LMs) can be challenging, as they are trained either to condition only on the past context or to perform narrowly scoped text-infilling. In this paper, we propose DeLorean, a new unsupervised decoding algorithm that can flexibly incorporate both the past and future contexts using onl…
EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
Shanghai Jiao Tong University（上海交通大学）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；Peng Cheng Laboratory（鹏城实验室）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Mohamed Bin Zayed University of Artificial Intelligence（Mohamed Bin Zayed人工智能大学）；Yinwang Intelligent Technology Co.（亿维智能技术有限公司）
University of California Irvine（加州大学欧文分校）；Meta；University of Chicago（芝加哥大学）
Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on understanding of the real world. In this paper we tease these factors apart by leveraging counterfactual conditionals, which force language models to predict unusual consequences based on hypothetical propositions. We introduce a set of tests drawn from psycholinguistic experiments, as well as larger-scale controlled datasets, to probe counterfactual predictions from a variety …
Harbin Institute of Technology（哈尔滨工业大学）；University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）
Open-domain dialogue generation suffers from the data insufficiency problem due to the vast size of potential responses. In this paper, we propose to explore potential responses by counterfactual reasoning. Given an observed response, the counterfactual reasoning model automatically infers the outcome of an alternative policy that could have been taken. The resulting counterfactual response synthesized in hindsight is of higher quality than the response synthesized from scratch. Training on the counterfactual responses under the adversarial learning framework helps to explore the high-reward a…
Counterfactual Reasoning with Knowledge Graph Embeddings
Faculty of Computer Science, University of Vienna（维也纳大学计算机学院）；UniVie Doctoral School Computer Science, University of Vienna（维也纳大学UniVie计算机博士学院）；Faculty of Philological and Cultural Studies, University of Vienna（维也纳大学语文学与文化学院）
As humans, we can modify our assumptions about a scene by imagining alternative objects or concepts in our minds. For example, we can easily anticipate the implications of the sun being overcast by rain clouds (e.g., the street will get wet) and accordingly prepare for that. In this paper, we introduce a new task/dataset called Commonsense Reasoning for Counterfactual Scene Imagination (CoSIm) which is designed to evaluate the ability of AI systems to reason about scene change imagination. In this task/dataset, models are given an image and an initial question-response pair about the image. Ne…
Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Jacobi Medical Center, Albert Einstein College of Medicine（雅各布医疗中心，阿尔伯特·爱因斯坦学院）；Department of Emergency Medicine, Beth Israel Deaconess Medical Center（贝斯以色列医疗中心急诊科）；Leaning machines（Leanings machines）
