VIRAASAT: Traversing Novel Paths for Indian Cultural Reasoning

2026-02-20

AI Summary

This work addresses the limited performance of large language models on multi-hop reasoning tasks involving culturally rich contexts such as Indian culture, where existing cultural evaluation benchmarks are often manually constructed, single-hop, and difficult to scale. To bridge this gap, the authors propose VIRAASAT—a semi-automated framework for generating multi-hop questions grounded in a comprehensive Indian cultural knowledge graph encompassing over 700 expert-curated entities, 13 cultural attributes, and all 36 administrative regions of India. They further introduce the Symbolic Chain-of-Manipulation (SCoM) framework, which enables models to internalize atomic operations over the knowledge graph and reliably traverse its topological structure. Experiments demonstrate that SCoM improves performance over standard chain-of-thought prompting by up to 20% on VIRAASAT, substantially overcoming bottlenecks in reasoning about low-probability cultural facts. The dataset and methodology are publicly released to advance research in culturally aware reasoning.

Technology Category

• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Natural Language Processing: Question Answering

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Large Language Models (LLMs) have made significant progress in reasoning tasks across various domains such as mathematics and coding. However, their performance deteriorates in tasks requiring rich socio-cultural knowledge and diverse local contexts, particularly those involving Indian Culture. Existing Cultural benchmarks are (i) Manually crafted, (ii) contain single-hop questions testing factual recall, and (iii) prohibitively costly to scale, leaving this deficiency largely unmeasured. To address this, we introduce VIRAASAT, a novel, semi-automated multi-hop approach for generating cultural specific multi-hop Question-Answering dataset for Indian culture. VIRAASAT leverages a Knowledge Graph comprising more than 700 expert-curated cultural artifacts, covering 13 key attributes of Indian culture (history, festivals, etc). VIRAASAT spans all 28 states and 8 Union Territories, yielding more than 3,200 multi-hop questions that necessitate chained cultural reasoning. We evaluate current State-of-the-Art (SOTA) LLMs on VIRAASAT and identify key limitations in reasoning wherein fine-tuning on Chain-of-Thought(CoT) traces fails to ground and synthesize low-probability facts. To bridge this gap, we propose a novel framework named Symbolic Chain-of-Manipulation (SCoM). Adapting the Chain-of-Manipulation paradigm, we train the model to simulate atomic Knowledge Graph manipulations internally. SCoM teaches the model to reliably traverse the topological structure of the graph. Experiments on Supervised Fine-Tuning (SFT) demonstrate that SCoM outperforms standard CoT baselines by up to 20%. We release the VIRAASAT dataset along with our findings, laying a strong foundation towards building Culturally Aware Reasoning Models.

Problem

• cultural reasoning
• Indian culture
• large language models
• multi-hop QA
• knowledge graph

Innovation

• VIRAASAT
• Symbolic Chain-of-Manipulation
• Cultural Reasoning
• Knowledge Graph
• Multi-hop QA