Inference of Abstraction for a Unified Account of Symbolic Reasoning from Data
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Inspired by empirical work in neuroscience for Bayesian approaches to brain function, we give a unified probabilistic account of various types of symbolic reasoning from data. We characterise them in terms of formal logic using the classical consequence relation, an empirical consequence relation, maximal consistent sets, maximal possible sets and maximum likelihood estimation. The theory gives new insights into reasoning towards human-like machine intelligence.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 0 of its 27 references that are in the map. First posted on arXiv 13 Feb 2024.
Builds on
0 of 27 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023A Simple Generative Model of Logical Reasoning and Statistical Learning
- 2025Inference of Abstraction for Grounded Predicate Logic
- 2026Neuro-symbolic PRM: Enhancing Scientific Reasoning via Structured Traces and Symbolic Verification
- 2026REASON: Accelerating Probabilistic Logical Reasoning for Scalable Neuro-Symbolic Intelligence
- 2026Probabilistic Extension of Neuro-Symbolic AGI Robots based on Belnap's Typed Intensional FOL
- 2023Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees
- 2025PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
- 2023Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems