Zobrazeno 1 - 10
of 195
pro vyhledávání: '"Bhatia, Sumit"'
Despite their remarkable capabilities, Large Language Models (LLMs) are found to be surprisingly sensitive to minor variations in prompts, often generating significantly divergent outputs in response to minor variations in the prompts, such as spelli
Externí odkaz:
http://arxiv.org/abs/2410.02185
Autor:
Furniturewala, Shaz, Jandial, Surgan, Java, Abhinav, Banerjee, Pragyan, Shahid, Simra, Bhatia, Sumit, Jaidka, Kokil
Existing debiasing techniques are typically training-based or require access to the model's internals and output distributions, so they are inaccessible to end-users looking to adapt LLM outputs for their particular needs. In this study, we examine w
Externí odkaz:
http://arxiv.org/abs/2405.10431
Autor:
Ganesan, Balaji, Pasha, Matheen Ahmed, Parkala, Srinivasa, Singh, Neeraj R, Mishra, Gayatri, Bhatia, Sumit, Patel, Hima, Naganna, Somashekar, Mehta, Sameep
Explaining neural model predictions to users requires creativity. Especially in enterprise applications, where there are costs associated with users' time, and their trust in the model predictions is critical for adoption. For link prediction in mast
Externí odkaz:
http://arxiv.org/abs/2403.09806
Instruction Tuning involves finetuning a language model on a collection of instruction-formatted datasets in order to enhance the generalizability of the model to unseen tasks. Studies have shown the importance of balancing different task proportions
Externí odkaz:
http://arxiv.org/abs/2403.08370
Autor:
Patnaik, Sohan, Changwal, Heril, Aggarwal, Milan, Bhatia, Sumit, Kumar, Yaman, Krishnamurthy, Balaji
Table understanding capability of Large Language Models (LLMs) has been extensively studied through the task of question-answering (QA) over tables. Typically, only a small part of the whole table is relevant to derive the answer for a given question
Externí odkaz:
http://arxiv.org/abs/2402.01155
Autor:
Banerjee, Pragyan, Java, Abhinav, Jandial, Surgan, Shahid, Simra, Furniturewala, Shaz, Krishnamurthy, Balaji, Bhatia, Sumit
Fairness in Language Models (LMs) remains a longstanding challenge, given the inherent biases in training data that can be perpetuated by models and affect the downstream tasks. Recent methods employ expensive retraining or attempt debiasing during i
Externí odkaz:
http://arxiv.org/abs/2311.05451
Ontologies are used in various domains, with RDF and OWL being prominent standards for ontology development. RDF is favored for its simplicity and flexibility, while OWL enables detailed domain knowledge representation. However, as ontologies grow la
Externí odkaz:
http://arxiv.org/abs/2308.04814
Sharing ideas through communication with peers is the primary mode of human interaction. Consequently, extensive research has been conducted in the area of conversational AI, leading to an increase in the availability and diversity of conversational
Externí odkaz:
http://arxiv.org/abs/2307.07255
Autor:
Shahid, Simra, Anand, Tanay, Srikanth, Nikitha, Bhatia, Sumit, Krishnamurthy, Balaji, Puri, Nikaash
Hierarchical Topic Models (HTMs) are useful for discovering topic hierarchies in a collection of documents. However, traditional HTMs often produce hierarchies where lowerlevel topics are unrelated and not specific enough to their higher-level topics
Externí odkaz:
http://arxiv.org/abs/2305.09258
Autor:
Renduchintala, H S V N S Kowndinya, Killamsetty, Krishnateja, Bhatia, Sumit, Aggarwal, Milan, Ramakrishnan, Ganesh, Iyer, Rishabh, Krishnamurthy, Balaji
A salient characteristic of pre-trained language models (PTLMs) is a remarkable improvement in their generalization capability and emergence of new capabilities with increasing model capacity and pre-training dataset size. Consequently, we are witnes
Externí odkaz:
http://arxiv.org/abs/2305.06677