no code implementations • 16 Nov 2023 • Kazuma Hashimoto, Karthik Raman, Michael Bendersky
Unlike the previous work, we introduce a novel labeling method, incremental utility, which estimates how much incremental knowledge is brought into the LLMs by a demonstration.
no code implementations • 14 Nov 2023 • Aditi Chaudhary, Karthik Raman, Michael Bendersky
Recent developments in large language models (LLMs) have shown promise in their ability to generate synthetic query-document pairs by prompting with as few as 8 demonstrations.
no code implementations • 14 Sep 2023 • Lingyu Gao, Aditi Chaudhary, Krishna Srinivasan, Kazuma Hashimoto, Karthik Raman, Michael Bendersky
In-context learning (ICL) i. e. showing LLMs only a few task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required.
no code implementations • 19 May 2023 • Aditi Chaudhary, Karthik Raman, Krishna Srinivasan, Kazuma Hashimoto, Mike Bendersky, Marc Najork
While our experiments demonstrate that these modifications help improve performance of QGen techniques, we also find that QGen approaches struggle to capture the full nuance of the relevance label space and as a result the generated queries are not faithful to the desired relevance label.
no code implementations • 21 Dec 2022 • Kazuma Hashimoto, Iftekhar Naim, Karthik Raman
Sequence labeling is a core task in text understanding for IE/IR systems.
no code implementations • 27 Oct 2022 • Krishna Srinivasan, Karthik Raman, Anupam Samanta, Lingrui Liao, Luca Bertelli, Mike Bendersky
Thus, in this paper we make the following contributions: (1) We demonstrate that Retrieval Augmentation of queries provides LLMs with valuable additional context enabling improved understanding.
no code implementations • 29 Sep 2022 • Kazuma Hashimoto, Karthik Raman
GROOT works by training a generative sequential labeling model to match the decoder output distribution with that of the (black-box) reward function.
no code implementations • 28 Sep 2022 • Sebastian Hofstätter, Jiecao Chen, Karthik Raman, Hamed Zamani
Retrieval-augmented generation models offer many benefits over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base.
no code implementations • 7 Jul 2022 • Sebastian Hofstätter, Jiecao Chen, Karthik Raman, Hamed Zamani
This paper studies multi-task training of retrieval-augmented generation models for knowledge-intensive tasks.
no code implementations • 16 Mar 2022 • Karthik Raman, Iftekhar Naim, Jiecao Chen, Kazuma Hashimoto, Kiran Yalasangi, Krishna Srinivasan
Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks.
no code implementations • 5 Nov 2021 • Debomita Chakraborty, Raghunathan Rengaswamy, Karthik Raman
Genetic circuit design is a well-studied problem in synthetic biology.
no code implementations • 25 Sep 2021 • Sai Saranga Das M, Karthik Raman
The vulnerability of networks to targeted attacks is an issue of widespread interest for policymakers, military strategists, network engineers and systems biologists alike.
3 code implementations • 2 Mar 2021 • Krishna Srinivasan, Karthik Raman, Jiecao Chen, Michael Bendersky, Marc Najork
First, WIT is the largest multimodal dataset by the number of image-text examples by 3x (at the time of writing).
Ranked #1 on Image Retrieval on WIT
no code implementations • 12 Feb 2021 • Sahana Gangadharan, Karthik Raman
An astonishingly diverse biomolecular circuitry orchestrates the functioning machinery underlying every living cell.
no code implementations • 30 Oct 2020 • Anand A. Rajasekar, Karthik Raman, Balaraman Ravindran
One challenging and essential task in biochemistry is the generation of novel molecules with desired properties.
no code implementations • 23 Oct 2020 • Aditi Chaudhary, Karthik Raman, Krishna Srinivasan, Jiecao Chen
In particular, by requiring the model to predict the language-specific token, the MLM objective disincentivizes learning a language-agnostic representation -- which is a key goal of multilingual pre-training.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Jiecao Chen, Liu Yang, Karthik Raman, Michael Bendersky, Jung-Jung Yeh, Yun Zhou, Marc Najork, Danyang Cai, Ehsan Emadzadeh
Pre-trained models like BERT (Devlin et al., 2018) have dominated NLP / IR applications such as single sentence classification, text pair classification, and question answering.
no code implementations • 1 Sep 2019 • Aditya Siddhant, Melvin Johnson, Henry Tsai, Naveen Arivazhagan, Jason Riesa, Ankur Bapna, Orhan Firat, Karthik Raman
The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model.
no code implementations • WS 2019 • Karan Singhal, Karthik Raman, Balder ten Cate
There has been significant interest recently in learning multilingual word embeddings -- in which semantically similar words across languages have similar embeddings.
no code implementations • 14 Apr 2014 • Karthik Raman, Thorsten Joachims
Thus, in this paper we study the problem of automatically inferring student grades from ordinal peer feedback, as opposed to existing methods that require cardinal peer feedback.