INCLUDE: A chain-of-thought based mixture of experts for inclusive language generation

Raja Chakravarthi, Bharathi, Priya Muthusamy Chinnan, Shunmuga, Kumar Kumaresan, Prasanna, & Ponnusamy, Rahul. (2026). INCLUDE: A chain-of-thought based mixture of experts for inclusive language generation. Knowledge-Based Systems, 341, 115747. https://doi.org/10.1016/j.knosys.2026.115747

Abstract

Developing intelligent inclusive language generation systems that promote inclusivity and mitigate harmful or exclusive terms is a key challenge in advancing Equity, Diversity and Inclusion (EDI) principles. Using inclusive language in communication helps create a respectful, bias free and mutual understanding between the peers, which is also essential for organizations to promote safe and equitable workspaces. Inclusive language involves neutrality, tone sensitivity and fairness across diverse contexts, enabling meaningful engagement without marginalization. Considering this, we propose INCLUDE, an inclusive language generator designed for promoting respectful and equitable communication in workplaces. We curated a non-inclusive vs inclusive pair dataset including real-world workplace, advertisements and HR policy discourse with annotated inclusive rewrites. The proposed framework employs three experts dedicated to inclusiveness, bias and stereotype free and contextual relevance to facilitate the learning of diverse semantics. To optimize these experts, we propose a self-calibration mechanism using meta-prompting guided by a novel multi-dimensional reward function. Extensive evaluations, including metrics LLM based assessments and human in the loop analysis shows that proposed model effectively counters non-inclusive language into contextually appropriate, inclusive and accessible responses while maintaining the original intent.

Funder

Research Ireland
Google

Publisher

Elsevier

Rights

CC BY

cb

Collections

Publications