4 citations · 17 across the 13 of their papers we have counts for
13 papers
KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training
Meghanadh Pulivarthi, Kushagra Bhushan, Vineet Kumar +5
LLMs acquire vast amounts of knowledge during pre-training, but often lack the specialized knowledge needed to answer questions from niche sources such as manuals or technical docu…
A Library of LLM Intrinsics for Retrieval-Augmented Generation
Marina Danilevsky, Kristjan Greenewald, Chulaka Gunasekara +13
In the developer community for large language models (LLMs), there is not yet a clean pattern analogous to a software library, to support very large scale collaboration. Even for t…
Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG
Kushagra Bhushan, Yatin Nandwani, Dinesh Khandelwal +4
Retrieval-Augmented Generation (RAG) has emerged as a prominent method for incorporating domain knowledge into Large Language Models (LLMs). While RAG enhances response relevance b…
Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models
Sonam Gupta, Yatin Nandwani, Asaf Yehudai +3
Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting…
Selective Self-Rehearsal: A Fine-Tuning Approach to Improve Generalization in Large Language Models
Sonam Gupta, Yatin Nandwani, Asaf Yehudai +4
Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting…
Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering
Saeel Sandeep Nachane, Ojas Gramopadhye, Prateek Chanda +5
In this paper, we propose a modified version of the MedQA-USMLE dataset, named MEDQA-OPEN, which contains open-ended medical questions without options to mimic clinical scenarios,…
BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
Gaurav Pandey, Yatin Nandwani, Tahira Naseem +6
Distribution matching methods for language model alignment such as Generation with Distributional Control (GDC) and Distributional Policy Gradient (DPG) have not received the same…
Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs
Yatin Nandwani, Vineet Kumar, Dinesh Raghu +2
A major concern in using deep learning based generative models for document-grounded dialogs is the potential generation of responses that are not \textit{faithful} to the underlyi…
A Solver-Free Framework for Scalable Learning in Neural ILP Architectures
Yatin Nandwani, Rishabh Ranjan, Mausam +1
There is a recent focus on designing architectures that have an Integer Linear Programming (ILP) layer within a neural model (referred to as Neural ILP in this paper). Neural ILP a…
Neural Models for Output-Space Invariance in Combinatorial Problems
Yatin Nandwani, Vidit Jain, Mausam +1
Recently many neural models have been proposed to solve combinatorial puzzles by implicitly learning underlying constraints using their solved instances, such as sudoku or graph co…
Matching Papers and Reviewers at Large Conferences
Kevin Leyton-Brown, Mausam, Yatin Nandwani +4
Peer-reviewed conferences, the main publication venues in CS, rely critically on matching highly qualified reviewers for each paper. Because of the growing scale of these conferenc…
CEAR: Cross-Entity Aware Reranker for Knowledge Base Completion
Keshav Kolluru, Mayank Singh Chauhan, Yatin Nandwani +2
Pre-trained language models (LMs) like BERT have shown to store factual knowledge about the world. This knowledge can be used to augment the information present in Knowledge Bases,…
Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces
Yatin Nandwani, Deepanshu Jindal, Mausam +1
Recent research has proposed neural architectures for solving combinatorial problems in structured output spaces. In many such problems, there may exist multiple solutions for a gi…