A Survey on Enhancing Causal Reasoning Ability of Large Language Models

• URL: http://arxiv.org/abs/2503.09326v1
• Date: Wed, 12 Mar 2025 12:20:31 GMT
• Title: A Survey on Enhancing Causal Reasoning Ability of Large Language Models
• Authors: Xin Li, Zhuo Cai, Shoujin Wang, Kun Yu, Fang Chen,
• Abstract summary: Large language models (LLMs) have recently shown remarkable performance in language tasks and beyond.<n>LLMs still face challenges in handling tasks that require robust causal reasoning ability, such as health-care and economic analysis.<n>This paper systematically reviews literature on how to strengthen LLMs' causal reasoning ability.
• Score: 15.602788561902038
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have recently shown remarkable performance in language tasks and beyond. However, due to their limited inherent causal reasoning ability, LLMs still face challenges in handling tasks that require robust causal reasoning ability, such as health-care and economic analysis. As a result, a growing body of research has focused on enhancing the causal reasoning ability of LLMs. Despite the booming research, there lacks a survey to well review the challenges, progress and future directions in this area. To bridge this significant gap, we systematically review literature on how to strengthen LLMs' causal reasoning ability in this paper. We start from the introduction of background and motivations of this topic, followed by the summarisation of key challenges in this area. Thereafter, we propose a novel taxonomy to systematically categorise existing methods, together with detailed comparisons within and between classes of methods. Furthermore, we summarise existing benchmarks and evaluation metrics for assessing LLMs' causal reasoning ability. Finally, we outline future research directions for this emerging field, offering insights and inspiration to researchers and practitioners in the area.

Related papers

• A Call for New Recipes to Enhance Spatial Reasoning in MLLMs [85.67171333213301]
  Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks. Recent studies have exposed critical limitations in their spatial reasoning capabilities. This deficiency in spatial reasoning significantly constrains MLLMs' ability to interact effectively with the physical world.
  arXiv  Detail & Related papers  (2025-04-21T11:48:39Z)
• Causality for Natural Language Processing [17.681875945732042]
  Causal reasoning is a cornerstone of human intelligence and a critical capability for artificial systems. This thesis delves into various dimensions of causal reasoning and understanding in large language models.
  arXiv  Detail & Related papers  (2025-04-20T08:11:11Z)
• A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond [88.5807076505261]
  Large Reasoning Models (LRMs) have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference. A growing concern lies in their tendency to produce excessively long reasoning traces. This inefficiency introduces significant challenges for training, inference, and real-world deployment.
  arXiv  Detail & Related papers  (2025-03-27T15:36:30Z)
• Can Large Language Models Act as Symbolic Reasoners? [0.0]
  Large language models (LLMs) have been impressive but have been critiqued as not being able to reason about their process and conclusions derived. This paper explores the current research in investigating symbolic reasoning and LLMs.
  arXiv  Detail & Related papers  (2024-10-28T20:01:50Z)
• CausalEval: Towards Better Causal Reasoning in Language Models [16.55801836321059]
  Causal reasoning (CR) is a crucial aspect of intelligence, essential for problem-solving, decision-making, and understanding the world.<n>While language models (LMs) can generate rationales for their outputs, their ability to reliably perform causal reasoning remains uncertain.<n>We introduce CausalEval, a review of research aimed at enhancing LMs for causal reasoning.
  arXiv  Detail & Related papers  (2024-10-22T04:18:19Z)
• From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models [56.9134620424985]
  Cross-modal reasoning (CMR) is increasingly recognized as a crucial capability in the progression toward more sophisticated artificial intelligence systems. The recent trend of deploying Large Language Models (LLMs) to tackle CMR tasks has marked a new mainstream of approaches for enhancing their effectiveness. This survey offers a nuanced exposition of current methodologies applied in CMR using LLMs, classifying these into a detailed three-tiered taxonomy.
  arXiv  Detail & Related papers  (2024-09-19T02:51:54Z)
• Evaluating Interventional Reasoning Capabilities of Large Language Models [58.52919374786108]
  Large language models (LLMs) are used to automate decision-making tasks. In this paper, we evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention. We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types. These benchmarks allow us to isolate the ability of LLMs to accurately predict changes resulting from their ability to memorize facts or find other shortcuts.
  arXiv  Detail & Related papers  (2024-04-08T14:15:56Z)
• Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey [25.732397636695882]
  Large language models (LLMs) have recently shown impressive performance on tasks involving reasoning. Despite these successes, the depth of LLMs' reasoning abilities remains uncertain.
  arXiv  Detail & Related papers  (2024-04-02T11:46:31Z)
• Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models [56.34029644009297]
  Large language models (LLMs) have demonstrated the ability to overcome various limitations of formal Knowledge Representation (KR) systems. LLMs excel most in abductive reasoning, followed by deductive reasoning, while they are least effective at inductive reasoning. We study single-task training, multi-task training, and "chain-of-thought" knowledge distillation fine-tuning technique to assess the performance of model.
  arXiv  Detail & Related papers  (2023-10-02T01:00:50Z)
• A Comprehensive Overview of Large Language Models [68.22178313875618]
  Large Language Models (LLMs) have recently demonstrated remarkable capabilities in natural language processing tasks. This article provides an overview of the existing literature on a broad range of LLM-related concepts.
  arXiv  Detail & Related papers  (2023-07-12T20:01:52Z)
• Towards Reasoning in Large Language Models: A Survey [11.35055307348939]
  It is not yet clear to what extent large language models (LLMs) are capable of reasoning. This paper provides a comprehensive overview of the current state of knowledge on reasoning in LLMs.
  arXiv  Detail & Related papers  (2022-12-20T16:29:03Z)

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.