Jump to Content
Karthik Raman

Karthik Raman

Karthik is a Senior Staff Research Scientist at Google Research. Along with the team he leads (Hummingbird), his work revolves around Large Language Models and making them more practically useful and usable. Prior to joining Google, Karthik received his PhD from Cornell University in 2015. A list of pre-Google publications can be found here: http://www.cs.cornell.edu/~karthik/publications.html
Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Preview abstract Sequence labeling is a core task in text understanding for IE/IR systems. Text generation models have increasingly become the go-to solution for such tasks (e.g., entity extraction and dialog slot filling). While most research has focused on the labeling accuracy, a key aspect -- of vital practical importance -- has slipped through the cracks: understanding model confidence. More specifically, we lack a principled understanding of how to reliably gauge the confidence of a model in its predictions for each labeled span. This paper aims to provide some empirical insights on estimating model confidence for generative sequence labeling. Most notably, we find that simply using the decoder's output probabilities is not the best in realizing well-calibrated confidence estimates. As verified over six public datasets of different tasks, we show that our proposed approach -- which leverages statistics from top-k predictions by a beam search -- significantly reduces calibration errors of the predictions of a generative sequence labeling model. View details
    Preview abstract In-Context Learning (ICL) is an emergent capability of Large Language Models (LLMs). Only a few demonstrations enable LLMs to be used as blackbox for new tasks. Previous studies have shown that using LLMs' outputs as labels is effective in training models to select demonstrations. Such a label is expected to estimate utility of a demonstration in ICL; however, it has not been well understood how different labeling strategies affect results on target tasks. This paper presents an analysis on different utility functions by focusing on LLMs' output probability given ground-truth output, and task-specific reward given LLMs' prediction. 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. We conduct experiments with instruction-tuned LLMs on binary/multi-class classification, segmentation, and translation across Arabic, English, Finnish, Japanese, and Spanish. Our results show that (1) the probability is effective when the probability values are distributed across the whole value range (on the classification tasks), and (2) the downstream metric is more robust when nuanced reward values are provided with long outputs (on the segmentation and translation tasks). We then show that the proposed incremental utility further helps ICL by contrasting how the LLMs perform with and without the demonstrations. View details
    Preview abstract Query-document relevance prediction is a critical problem in Information Retrieval systems. This problem has increasingly been tackled using (pretrained) transformer-based models which are finetuned using large collections of labeled data. However, in specialized domains such as e-commerce and healthcare, the viability of this approach is limited by the dearth of large in-domain data. To address this paucity, recent methods leverage these powerful models to generate high-quality task and domain-specific synthetic data. Prior work has largely explored synthetic data generation or query generation (QGen) for Question-Answering (QA) and binary (yes/no) relevance prediction, where for instance, the QGen models are given a document, and trained to generate a query relevant to that document. However in many problems, we have a more fine-grained notion of relevance than a simple yes/no label. Thus, in this work, we conduct a detailed study into how QGen approaches can be leveraged for nuanced relevance prediction. We demonstrate that – contrary to claims from prior works – current QGen approaches fall short of the more conventional cross-domain transfer-learning approaches. Via empirical studies spanning three public e-commerce benchmarks, we identify new shortcomings of existing QGen approaches – including their inability to distinguish between different grades of relevance. To address this, we introduce label-conditioned QGen models which incorporates knowledge about the different relevance. 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. View details
    Preview abstract Large Language Models (LLMs) have shown impressive results on a variety of text understanding tasks. Search queries though pose a unique challenge, given their short-length and lack of nuance or context. Complicated feature engineering efforts do not always lead to downstream improvements as their performance benefits may be offset by increased complexity of knowledge distillation. 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. While Retrieval Augmentation typically increases latency of LMs (thus hurting distillation efficacy), (2) we provide a practical and effective way of distilling Retrieval Augmentation LLMs. Specifically, we use a novel two-stage distillation approach that allows us to carry over the gains of retrieval augmentation, without suffering the increased compute typically associated with it. (3) We demonstrate the benefits of the proposed approach on a billion-scale, real-world query understanding system resulting in an X\% improvement. Via extensive experiments, including on public benchmarks, we believe this work offers a recipe for practical use of retrieval-augmented query understanding. View details
    Preview abstract Sequential labeling is a fundamental NLP task, forming the backbone of many applications. Supervised learning of Seq2Seq models (like T5) has shown great success on these problems. However there remains a significant disconnect between the training objectives of these models vs the metrics and desiderata we care about in practical applications. For example, a practical sequence tagging application may want to optimize for a certain precision-recall trade-off (of the top-k predictions) which is quite different from the standard objective of maximizing the likelihood of the gold labeled sequence. Thus to bridge this gap, we propose GROOT -- a simple yet effective framework for Generative Reward Optimization Of Text sequences. GROOT works by training a generative sequential labeling model to match the decoder output distribution with that of the (black-box) reward function. Using an iterative training regime, we first generate prediction candidates, then correct errors in them, and finally contrast those candidates (based on their reward values). As demonstrated via extensive experiments on four public benchmarks, GROOT significantly improves all reward metrics. Furthermore, GROOT also leads to improvements of the overall decoder distribution as evidenced by the quality gains of the top- candidates. View details
    Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling
    Sebastian Hofstätter
    Jiecao Chen
    Hamed Zamani
    ICML 2022 Workshop on Knowledge Retrieval and Language Models
    Preview abstract This paper studies multi-task training of retrieval-augmented generation models for knowledge-intensive tasks. We propose to clean the training set by utilizing a distinct property of knowledge-intensive generation: The connection of query-answer pairs to items in the knowledge base. We filter training examples via a threshold of confidence on the relevance labels, whether a pair is answerable by the knowledge base or not.We train a single Fusion-in-Decoder (FiD) generator on seven combined tasks of the KILT benchmark. The experimental results suggest that our simple yet effective approach substantially improves competitive baselines on two strongly imbalanced tasks; and shows either smaller improvements or no significant regression on the remaining tasks. Furthermore, we demonstrate our multi-task training with relevance label sampling scales well with increased model capacity and achieves state-of-the-art results in five out of seven KILT tasks. View details
    Preview abstract Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq problem requires deciding the formats of the input and output sequences. However, we lack a principled understanding of the trade-offs associated with these formats (such as the effect on model accuracy, sequence length, multilingual generalization, hallucination). In this paper, we rigorously study different *formats* one could use for casting input text sentences and their output labels into the "input" and "target" of a Seq2Seq model. Along the way, we introduce a new format, which we show to not only be simpler but also more effective. Additionally the new formats demonstrate significant gains in the multilingual settings -- both zero-shot transfer learning and joint training. Lastly, we find that the new formats are more robust and almost completely devoid of the danger of *hallucination* that often plagues existing formats. With well over a 1000 experiments studying 14 different formats, over 7 diverse public benchmarks -- including 3 multilingual datasets spanning 7 languages -- we believe our findings provide a strong empirical basis in understanding how we should tackle sequence tagging tasks. View details
    FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation
    Sebastian Florentin Hofstätter
    Jiecao Chen
    Hamed Zamani
    arXiv preprint arXiv:2209.14290 (2022)
    Preview abstract 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. However, they are also more complex systems and need to handle long inputs. In this work, we introduce FiD-Light to strongly increase the efficiency of the state-of-the-art retrieval-augmented FiD model, while maintaining the same level of effectiveness. Our FiD-Light model constrains the information flow from the encoder (which encodes passages separately) to the decoder (using concatenated encoded representations). Furthermore, we adapt FiD-Light with re-ranking capabilities through textual source pointers, to improve the top-ranked provenance precision. Our experiments on a diverse set of seven knowledge intensive tasks (KILT) show FiD-Light consistently improves the Pareto frontier between query latency and effectiveness. FiD-Light with source pointing sets substantial new state-of-the-art results on six KILT tasks for combined text generation and provenance retrieval evaluation, while maintaining reasonable efficiency. View details
    WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning
    Jiecao Chen
    Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '21) (2021)
    Preview abstract The milestone improvements brought about by deep representation learning and pre-training techniques have led to large performance gains across downstream NLP, IR and Vision tasks. Multimodal modeling techniques aim to leverage high-quality visio-linguistic datasets for learning complementary information (across image and text modalities). In this paper, we introduce the Wikipedia-based Image Text (WIT) Dataset to better facilitate multimodal, multilingual learning. WIT is composed of 11 million+ unique images with over 37 million entity rich text descriptions associated with these images in Wikipedia from over 100 languages. Its size enables WIT to be used as a pretraining dataset for multimodal models, as we show when applied to downstream tasks such as image-text retrieval. WIT has four main and unique advantages. First, WIT is the largest multimodal dataset (at the time of writing). Second, it is massively multilingual (first of its kind) with coverage over 100+ languages (each of which has at least 10K examples) and provides cross-lingual texts for many images. Third, it represents a more diverse set of concepts and real world entities relative to what previous datasets cover. Lastly, as we demonstrate empirically, WIT provides a very challenging real-world test set that empirically highlights the need for learning improvements in tasks such as Retrieval and Captioning. View details
    Google COVID-19 Search Trends Symptoms Dataset: Anonymization Process Description
    Akim Kumok
    Chaitanya Kamath
    Charlotte Stanton
    Damien Desfontaines
    Evgeniy Gabrilovich
    Gerardo Flores
    Gregory Alexander Wellenius
    Ilya Eckstein
    John S. Davis
    Katie Everett
    Krishna Kumar Gadepalli
    Rayman Huang
    Shailesh Bavadekar
    Thomas Ludwig Roessler
    Venky Ramachandran
    Yael Mayer
    Arxiv.org, N/A (2020)
    Preview abstract This report describes the aggregation and anonymization process applied to the initial version of COVID-19 Search Trends symptoms dataset, a publicly available dataset that shows aggregated, anonymized trends in Google searches for symptoms (and some related topics). The anonymization process is designed to protect the daily search activity of every user with \varepsilon-differential privacy for \varepsilon = 1.68. View details
    Preview abstract Pre-trained multilingual language models such as mBERT have shown immense gains for several natural language processing (NLP) tasks, especially in the zero-shot cross-lingual setting. Most, if not all, of these pre-trained models rely on the masked-language modeling (MLM) objective as the key language learning objective. The principle behind these approaches is that predicting the masked words with the help of the surrounding text helps learn potent contextualized representations. Despite the strong representation learning capability enabled by MLM, we demonstrate an inherent limitation of MLM for multilingual representation learning. 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. Therefore to encourage better cross-lingual representation learning we propose the DICT-MLM method. DICT-MLM works by incentivizing the model to be able to predict not just the original masked word, but potentially any of its cross-lingual synonyms as well. Our empirical analysis on multiple downstream tasks spanning 30+ languages, demonstrates the efficacy of the proposed approach and its ability to learn better multilingual representations. View details
    Preview abstract Pre-trained models like BERT have dominated NLP / IR applications such as single sentence classification, text pair classification, and question answering. However, deploying these models in real systems is highly non-trivial due to their exorbitant computational costs. A common remedy to this is knowledge distillation, leading to faster inference. However –as we show here – existing works are not optimized for dealing with pairs (or tuples) of texts. Consequently, they are either not scalable or demonstrate subpar performance. In this work,we propose DiPair— a novel framework for distilling fast and accurate models on text pair tasks. Coupled with an end-to-end training strategy, DiPair is both highly scalable and offers improved quality-speed tradeoffs. Empirical studies conducted on both academic and real-world e-commerce benchmarks demonstrate the efficacy of the proposed approach with speedups of over 350x and minimal quality drop relative to the cross-attention teacherBERT model. View details
    Preview abstract Recently proposed Massively Multilingual Neural Machine Translation system has been shown to be capable of translating 102 languages to and from English within a single model. In this paper, we evaluate the cross-lingual effectiveness of representations from the encoder of such a model on 5 downstream classification and sequence tagging tasks spanning more than 50 languages. We compare our results to a strong multilingual baseline, BERT and show modest gains on zero-shot cross-lingual transfer in 4 out of these 5 tasks. Our results provide strong insight into how applicable the representations learned from multilingual machine translation are, across languages and tasks. View details
    Learning Multilingual Word Embeddings Using Image-Text Data
    Karan Singhal
    Balder ten Cate
    Proceedings of 2019 NAACL HLT Workshop on Shortcomings in Vision and Language (SiVL)
    Preview abstract There has been significant interest recently in learning multilingual word embeddings -- in which semantically similar words across languages have similar embeddings. State-of-the-art approaches have relied on expensive labeled data, which is unavailable for low-resource languages, or have involved post-hoc unification of monolingual embeddings. In the present paper, we investigate the efficacy of multilingual embeddings learned from weakly-supervised image-text data. In particular, we propose methods for learning multilingual embeddings using image-text data, by enforcing similarity between the representations of the image and that of the text. Our experiments reveal that even without using any expensive labeled data, a bag-of-words-based embedding model trained on image-text data achieves performance comparable to the the state-of-the-art on crosslingual semantic similarity tasks. View details
    Understanding intrinsic diversity in web search: Improving whole-session relevance
    Paul N. Bennett
    Kevyn Collins-Thompson
    ACM Transactions on Information Systems (TOIS), vol. 32 (2014), pp. 1-45
    Bayesian Ordinal Peer Grading
    Thorsten Joachims
    Proceedings of the Second (2015) ACM conference on Learning@ Scale (2014)
    Methods for Ordinal Peer Grading
    Thorsten Joachims
    Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM (2014), pp. 1037-1046
    Toward Whole-session Relevance: Exploring Intrinsic Diversity in Web Search
    Paul N. Bennett
    Kevyn Collins-Thompson
    Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval (2013)
    Learning socially optimal information systems from egoistic users
    Thorsten Joachims
    Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings, Part II 13, pp. 128-144
    Stable coactive learning via perturbation
    Thorsten Joachims
    Pannaga Shivaswamy
    Tobias Schnabel
    International conference on machine learning (2013), pp. 837-845
    Beyond myopic inference in big data pipelines
    Adith Swaminathan
    Johannes Gehrke
    Thorsten Joachims
    Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining (2013), pp. 86-94