Research map / Probabilistic and scientific modeling / Causal discovery
Rational Inference Patterns Based on Conditional Logic
Christian Eichhorn, Gabriele Kern-Isberner, Marco Ragni
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add a second conditional (library open) to the suppression task | Human reasoners (cited study) · Suppression task, Modus Ponens | endorsement %: 96 % -> 38 % | Hurt |
| Add additional conditional in Modus Tollens formulation | Human reasoners (cited study) · Suppression task, Modus Tollens | endorsement %: 92 % -> 33 % | Hurt |
| Use counterfactual instead of factual conditional | Human reasoners (Thompson and Byrne 2002) · Denial of Antecedent | endorsement %: 30% -> 50% | Improved |
| Use counterfactual instead of factual conditional | Human reasoners (Thompson and Byrne 2002) · Modus Tollens | endorsement %: 68% -> 85% | Improved |
| Use counterfactual instead of factual conditional | Human reasoners (Byrne and Tasso 1999) · Modus Tollens | endorsement %: 42% -> 66% | Improved |
| Use counterfactual instead of factual conditional | Human reasoners (Byrne and Tasso 1999) · Denial of Antecedent | endorsement %: 39% -> 59% | Improved |
| Use counterfactual instead of factual conditional | Human reasoners · Modus Ponens and Affirmation of Consequent | endorsement % | No clear effect |
| Remove weak conditional delta3 from the knowledge base (ablation) | Explanation Generator for counterfactual pattern · Pattern (MP, MT, not AC, DA) | pattern reproduced | Hurt |
| Treat the near-chance DA endorsement as not applied (50% DA) | Inference pattern modelling · Counterfactual study | explaining knowledge base | Mixed |
Closest papers by meaning
- RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning (ICML 2025 · similarity 0.86)
- Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement (ICLR 2024 · similarity 0.86)
- Nuance Matters: Probing Epistemic Consistency in Causal Reasoning (AAAI 2025 · similarity 0.85)
- Thought Branches: Interpreting LLM Reasoning Requires Resampling (ICLR 2026 · similarity 0.85)
- From Probability to Counterfactuals: the Increasing Complexity of Satisfiability in Pearl's Causal Hierarchy (ICLR 2025 · similarity 0.84)
- Causal Abstraction Inference under Lossy Representations (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
