2 papers
cs.CL2026
KiranaBench: Can a Language Model Run a Neighbourhood Shop?
Bhuvan Arora, Ankita Karmakar, Chaitanya Jain +10
Large language model (LLM) agents are increasingly evaluated on long-horizon tasks, including autonomously running a business. Existing benchmarks for this setting are almost exclu…
cs.CL2026
DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs
Bhuvan Arora, Devesh Saraogi, Sravya Varada +1
Large language models (LLMs) are increasingly deployed in globally used assistants, yet their default choices in culturally grounded everyday situations can systematically favour s…