7 papers
Known Intents, New Combinations: Clause-Factorized Decoding for Compositional Multi-Intent Detection
Abhilash Nandy
Multi-intent detection papers usually ask whether a model can recover multiple intents from one utterance. We ask a harder and, for deployment, more useful question: can it recover…
: A Large and Diverse Multimodal Benchmark for evaluating the ability of Vision-Language Models to understand Rebus Puzzles
Trishanu Das, Abhilash Nandy, Khush Bajaj +1
Understanding Rebus Puzzles (Rebus Puzzles use pictures, symbols, and letters to represent words or phrases creatively) requires a variety of skills such as image recognition, cogn…
Leveraging Large Language Models for Predictive Analysis of Human Misery
Bishanka Seal, Rahul Seetharaman, Aman Bansal +1
This study investigates the use of Large Language Models (LLMs) for predicting human-perceived misery scores from natural language descriptions of real-world scenarios. The task is…
Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs
Ananth Muppidi, Abhilash Nandy, Sambaran Bandyopadhyay
The performance of large language models in domain-specific tasks necessitates fine-tuning, which is computationally expensive and technically challenging. This paper focuses on pa…
REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback
Aniruddha Roy, Pretam Ray, Abhilash Nandy +2
Instruction-based Large Language Models (LLMs) have proven effective in numerous few-shot or zero-shot Natural Language Processing (NLP) tasks. However, creating human-annotated in…
: Domain-Specific Fast Continual Pre-training Technique using Document-Level Metadata and Taxonomy
Abhilash Nandy, Manav Nitin Kapadnis, Sohan Patnaik +3
In this paper, we propose (Fast Continual Pre-training Technique using Document Level Metadata and Taxonomy), a novel, compute-efficient framework that utilizes Document…