← Search

Arnav Goel

2 accepted papers

2025

Attributing Culture-Conditioned Generations to Pretraining Corpora

ICLR 2025poster

In open-ended generative tasks like narrative writing or dialogue, large language models often exhibit cultural biases, showing limited knowledge and generating templated outputs for less prevalent cultures. Recent works show that these biases may stem from uneven cultural representation in pretrain…

2024

LLMGuard: Guarding against Unsafe LLM Behavior

AAAI 2024technical

Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns. To alleviate this, we pres…

Cited by 11SourcePDFScholar