Causal Question Answering with Reinforcement Learning

• URL: http://arxiv.org/abs/2311.02760v2
• Date: Mon, 25 Mar 2024 08:57:47 GMT
• Title: Causal Question Answering with Reinforcement Learning
• Authors: Lukas Blübaum, Stefan Heindorf,
• Abstract summary: Causal questions inquire about causal relationships between different events or phenomena. In this paper, we aim to answer causal questions with a causality graph. We introduce an Actor-Critic-based agent which learns to search through the graph to answer causal questions.
• Score: 0.3499042782396683
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Causal questions inquire about causal relationships between different events or phenomena. They are important for a variety of use cases, including virtual assistants and search engines. However, many current approaches to causal question answering cannot provide explanations or evidence for their answers. Hence, in this paper, we aim to answer causal questions with a causality graph, a large-scale dataset of causal relations between noun phrases along with the relations' provenance data. Inspired by recent, successful applications of reinforcement learning to knowledge graph tasks, such as link prediction and fact-checking, we explore the application of reinforcement learning on a causality graph for causal question answering. We introduce an Actor-Critic-based agent which learns to search through the graph to answer causal questions. We bootstrap the agent with a supervised learning procedure to deal with large action spaces and sparse rewards. Our evaluation shows that the agent successfully prunes the search space to answer binary causal questions by visiting less than 30 nodes per question compared to over 3,000 nodes by a naive breadth-first search. Our ablation study indicates that our supervised learning strategy provides a strong foundation upon which our reinforcement learning agent improves. The paths returned by our agent explain the mechanisms by which a cause produces an effect. Moreover, for each edge on a path, our causality graph provides its original source allowing for easy verification of paths.

Related papers

• Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering [60.6042489577575]
  We introduce Konstruktor - an efficient and robust approach that breaks down the problem into three steps. Our approach integrates language models and knowledge graphs, exploiting the power of the former and the interpretability of the latter. We show that for relation detection, the most challenging step of the workflow, a combination of relation classification/generation and ranking outperforms other methods.
  arXiv  Detail & Related papers  (2024-09-24T09:19:11Z)
• Unsupervised Pairwise Causal Discovery on Heterogeneous Data using Mutual Information Measures [49.1574468325115]
  Causal Discovery is a technique that tackles the challenge by analyzing the statistical properties of the constituent variables. We question the current (possibly misleading) baseline results on the basis that they were obtained through supervised learning. In consequence, we approach this problem in an unsupervised way, using robust Mutual Information measures.
  arXiv  Detail & Related papers  (2024-08-01T09:11:08Z)
• CELLO: Causal Evaluation of Large Vision-Language Models [9.928321287432365]
  Causal reasoning is fundamental to human intelligence and crucial for effective decision-making in real-world environments. We introduce a fine-grained and unified definition of causality involving interactions between humans and objects. We construct a novel dataset, CELLO, consisting of 14,094 causal questions across all four levels of causality.
  arXiv  Detail & Related papers  (2024-06-27T12:34:52Z)
• CausalLP: Learning causal relations with weighted knowledge graph link prediction [5.3454230926797734]
  CausalLP formulates the issue of incomplete causal networks as a knowledge graph completion problem. The use of knowledge graphs to represent causal relations enables the integration of external domain knowledge. Two primary tasks are supported by CausalLP: causal explanation and causal prediction.
  arXiv  Detail & Related papers  (2024-04-23T20:50:06Z)
• CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning [2.7446241148152253]
  CORE is a reinforcement learning-based approach for causal discovery and intervention planning. Our results demonstrate that CORE generalizes to unseen graphs and efficiently uncovers causal structures. CORE scales to larger graphs with up to 10 variables and outperforms existing approaches in structure estimation accuracy and sample efficiency.
  arXiv  Detail & Related papers  (2024-01-30T12:57:52Z)
• Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions [93.40614719648386]
  Large language models (LLMs) are capable of answering knowledge-intensive complex questions with chain-of-thought (CoT) reasoning. Recent works turn to retrieving external knowledge to augment CoT reasoning. We propose a novel approach: Probabilistic Tree-of-thought Reasoning (ProbTree)
  arXiv  Detail & Related papers  (2023-11-23T12:52:37Z)
• Active Bayesian Causal Inference [72.70593653185078]
  We propose Active Bayesian Causal Inference (ABCI), a fully-Bayesian active learning framework for integrated causal discovery and reasoning. ABCI jointly infers a posterior over causal models and queries of interest. We show that our approach is more data-efficient than several baselines that only focus on learning the full causal graph.
  arXiv  Detail & Related papers  (2022-06-04T22:38:57Z)
• Tell me why! -- Explanations support learning of relational and causal structure [24.434551113103105]
  Explanations play a considerable role in human learning, especially in areas that remain major challenges for AI. We show that reinforcement learning agents might likewise benefit from explanations. Our results suggest that learning from explanations is a powerful principle that could offer a promising path towards training more robust and general machine learning systems.
  arXiv  Detail & Related papers  (2021-12-07T15:09:06Z)
• Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning [76.00395335702572]
  A central goal for AI and causality is the joint discovery of abstract representations and causal structure. Existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs. In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them.
  arXiv  Detail & Related papers  (2021-07-02T05:44:56Z)
• To do or not to do: finding causal relations in smart homes [2.064612766965483]
  This paper introduces a new way to learn causal models from a mixture of experiments on the environment and observational data. The core of our method is the use of selected interventions, especially our learning takes into account the variables where it is impossible to intervene. We use our method on a smart home simulation, a use case where knowing causal relations pave the way towards explainable systems.
  arXiv  Detail & Related papers  (2021-05-20T22:36:04Z)
• Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding [140.5911760063681]
  We propose a novel dataset named Knowledge-Routed Visual Question Reasoning for VQA model evaluation. We generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs.
  arXiv  Detail & Related papers  (2020-12-14T00:33:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.