5 papers
On Defining Erasure Harms for NLP
Yu Lu Liu, Arnav Goel, Jackie Chi Kit Cheung +3
The deployment of NLP systems has raised concerns about harms they might produce, including representational harms. Recent literature has begun to conceptualize and measure one suc…
MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation
Mehul Agarwal, Aditya Aggarwal, Arnav Goel +2
While multilingual large language models (LLMs) perform well on high-level tasks like translation and question answering, their ability to handle grammatical gender and morphologic…
HORIZON: A Benchmark for In-the-wild User Behaviour Modeling
Arnav Goel, Pranjal A Chitale, Bhawna Paliwal +2
User behavior in the real world is diverse, cross-domain, and spans long time horizons. Existing user modeling benchmarks however remain narrow, focusing mainly on short sessions a…
Enhancing Scientific Visual Question Answering via Vision-Caption aware Supervised Fine-Tuning
Janak Kapuriya, Anwar Shaikh, Arnav Goel +8
In this study, we introduce Vision-Caption aware Supervised FineTuning (VCASFT), a novel learning paradigm designed to enhance the performance of smaller Vision Language Models(VLM…
Attributing Culture-Conditioned Generations to Pretraining Corpora
Huihan Li, Arnav Goel, Keyu He +1
In open-ended generative tasks like narrative writing or dialogue, large language models often exhibit cultural biases, showing limited knowledge and generating templated outputs f…