AI You Can Trust

Communication-Aware, Ambiguity-Sensitive, and Interpretable NLP for High-Stakes Domains

Abstract

Artificial intelligence systems increasingly interpret human communication in high-stakes settings such as mental health, legal reasoning, and cybersecurity contexts. Yet current large language models often produce fluent but incorrect outputs, especially when meaning depends on ambiguity, hidden mental states, or community-specific communication patterns. We argue that trustworthy AI in such settings requires a shift away from purely generative pipelines toward hybrid, communication-aware, structure-aware, and ambiguity-sensitive NLP that supports interpretable and reliable inference. We present a position supported by three complementary research directions: structure-aware analysis of mental health signals, ambiguity-aware reasoning for explainable inference in domains such as legal interpretation, and communication-driven risk modeling in open-source ecosystems. Across these case studies, we argue that reliable high-stakes AI must integrate linguistic and interaction structure, socio-communicative context, and explicit reasoning, while preserving human oversight and ethical safeguards.