Somak Aditya

Multilingual CheckList: Generation and Evaluation

2022

Multilingual evaluation benchmarks usually contain limited high-resource languages and do not test models for specific linguistic capabilities.CheckList (Ribeiro et al., 2020) is a template-based evaluation approach that tests models for specific capabilities.The CheckList template creation …

Text2Afford: Probing Object Affordance Prediction abilities of Language Models solely from Text

2024

We investigate the knowledge of object affordances in pre-trained language models (LMs) and pre-trained Vision-Language models (VLMs).A growing body of literature shows that PTLMs fail inconsistently and nonintuitively, demonstrating a lack of reasoning and grounding.To …