mlsanityData to 14 Oct 2026

Abductive Reasoning with the GPT-4 Language Model: Case studies from criminal investigation, medical practice, scientific research

arXiv 2307.10250 ↗First posted 17 Jul 2023cs.AIcited by 6

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

This study evaluates the GPT-4 Large Language Model's abductive reasoning in complex fields like medical diagnostics, criminology, and cosmology. Using an interactive interview format, the AI assistant demonstrated reliability in generating and selecting hypotheses. It inferred plausible medical diagnoses based on patient data and provided potential causes and explanations in criminology and cosmology. The results highlight the potential of LLMs in complex problem-solving and the need for further research to maximize their practical applications.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 1 of its 17 references that are in the map. First posted on arXiv 17 Jul 2023.

Builds on

1 of 17 references.

References · 1

  1. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2024AI and Generative AI for Research Discovery and Summarizationcited by 4
  2. 2025Recommending Actionable Strategies: A Semantic Approach to Integrating Analytical Frameworks with Decision Heuristicscited by 3
  3. 2025Quantum Abduction: A New Paradigm for Reasoning under Uncertaintycited by 2
  4. 2026AILS-NTUA at SemEval-2026 Task 12: Graph-Based Retrieval and Reflective Prompting for Abductive Event Reasoningcited by 2
  5. 2025A Beautiful Mind: Principles and Strategies for AI-Augmented Human Reasoningcited by 0
  6. 2025Hybrid Reasoning Systems That Prioritize and Enhance Human Intelligencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs
  2. 2023How well do SOTA legal reasoning models support abductive reasoning?
  3. 2026Abductive Reasoning with Syllogistic Forms in Large Language Models
  4. 2025GEAR: A General Evaluation Framework for Abductive Reasoning
  5. 2026Medical Reasoning with Large Language Models: A Survey and MR-Bench
  6. 2026Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference
  7. 2023Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine
  8. 2022True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4