6 papers
ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models
Somnath Banerjee, Sayan Layek, Sayantan Adak +3
Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can a…
MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
Sayantan Adak, Somnath Banerjee, Rajarshi Mandal +4
Online memes are a powerful yet challenging medium for content moderation, often masking harmful intent behind humor, irony, or cultural symbolism. Conventional moderation systems…
TEXT2AFFORD: Probing Object Affordance Prediction abilities of Language Models solely from Text
Sayantan Adak, Daivik Agrawal, Animesh Mukherjee +1
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…
AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models
Sayantan Adak, Pratyush Chatterjee, Somnath Banerjee +3
Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implicatio…
REVERSUM: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives
Sayantan Adak, Pauras Mangesh Meher, Paramita Das +1
Wikipedia is an invaluable resource for factual information about a wide range of entities. However, the quality of articles on less-known entities often lags behind that of the we…
RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents
Sayantan Adak, Animesh Mukherjee
Inspirational quotes from famous individuals are often used to convey thoughts in news articles, essays, and everyday conversations. In this paper, we propose a novel context-based…