paper
Operads for compositional reasoning in LLMs
paperactiveprovisional
operads-for-compositional-reasoning-in-llms-aeb0ee22·1 events·first seen 5d agoAliases: Operads for compositional reasoning in LLMs
Co-occurring entities
More like this (12)
Operadic consistency: a label-free signal for compositional reasoning failures in LLMscode synthesis LLMsFrom Correctness to Utility: Gain-Based Prefix Evaluation for LLM ReasoningMeta-Learning for CompositionalityAgentic Chain-of-Thought Steering for Efficient and Controllable LLM ReasoningWhich Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMsLLM inferenceScaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight VerifierReasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday ReasoningA sleep-like consolidation mechanism for LLMsBeyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Modelslong-context LLMs
Recent events (1)
Operads proposed as mathematical foundation for LLM question decomposition and consistency
Researchers propose operads — algebraic structures modeling many-in, one-out compositions — as a rigorous mathematical framework for question decomposition in LLMs. They define a 'questions operad' where QA models are interpreted as algebras, and introduce 'operadic consistency' as a measure of whether a model's answers agree across partial collapses of a decomposition tree. A companion empirical paper reports operadic consistency is strongly correlated with accuracy across twelve LLMs and four multi-hop QA datasets, outperforming temperature-based self-consistency baselines. The work attempts to give formal grounding to a widely-used but theoretically underspecified reasoning strategy.