mlsanityData to 14 Oct 2026

IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMs

arXiv 2409.05559 ↗First posted 9 Sep 2024cs.AIcited by 9

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large language models (LLMs) have developed rapidly, and their reasoning capabilities have become a hot research topic. However, there is still limited exploration of abductive reasoning. The multi-perspective and multi-level of causes is one of the core challenges of abductive reasoning, which cannot be solved well by existing methods. We construct a specialized dataset named DeepAbduction, which is designed for tracing the causes of pollution and disease, addressing the lack of datasets in this field. We propose Inverse-Forward Abductive Reasoning (IFAR) framework for LLMs multi-perspective and multi-level abductive reasoning. IFAR is zero-shot and combines generalized backward reasoning with relation-by-relation forward verification. Experimental results show that IFAR achieves an improvement of approximately 40% in the F1 score compared to other methods under mainstream LLMs, while maintaining a balance between recall and precision. Furthermore, IFAR enhances the performance of non-reasoning LLMs to surpass LLMs which have been trained for reasoning, and remains effective when applied to the latter. Code will be released after the acceptance of our work.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 24 of its 41 references that are in the map. First posted on arXiv 9 Sep 2024.

Builds on

24 of 41 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Information Re-Organization Improves Reasoning in Large Language Models22 Apr
  2. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb
  3. 2022Towards Reasoning in Large Language Models: A Survey20 Dec
  4. 2022AbductionRules: Training Transformers to Explain Unexpected Inputs23 Mar

Other references · 20

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  7. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  8. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  9. 2021GPT Understands, Toocited by 716
  10. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 324
  11. 2019Abductive Commonsense Reasoningcited by 301
  12. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 168
8 more
  1. 2023XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameterscited by 92
  2. 2023Integrating Large Language Model for Improved Causal Discoverycited by 54
  3. 2024ProLLaMA: A Protein Large Language Model for Multi-Task Protein Language Processingcited by 53
  4. 2023TrafficGPT: Viewing, Processing and Interacting with Traffic Foundation Modelscited by 45
  5. 2024Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectivescited by 30
  6. 2024LLMs Are Prone to Fallacies in Causal Inferencecited by 23
  7. 2024Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting Potcited by 11
  8. 2019Abductive Reasoning as Self-Supervision for Common Sense Question Answeringcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 111
  2. 2025CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routingcited by 6
  3. 2025From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Modelscited by 5
  4. 2026Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMscited by 5
  5. 2026AILS-NTUA at SemEval-2026 Task 12: Graph-Based Retrieval and Reflective Prompting for Abductive Event Reasoningcited by 2
  6. 2025Investigating Advanced Reasoning of Large Language Models via Black-Box Environment Interactioncited by 1
  7. 2026IFDNS: An Iterative Feedback-Driven Neuro-Symbolic Method for Faithful Logical Reasoningcited by 0
  8. 2026GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Modelscited by 0
  9. 2026CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GEAR: A General Evaluation Framework for Abductive Reasoning
  2. 2026SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models
  3. 2026LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos
  4. 2026Abductive Reasoning with Syllogistic Forms in Large Language Models
  5. 2025Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises
  6. 2024A Critical Review of Causal Reasoning Benchmarks for Large Language Models
  7. 2025Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery
  8. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causality