Adam Lelkes
I am a Staff Research Scientist at Google DeepMind. My research impacts key Google products, including Search ranking, AI Overviews, AI Mode, and Gemini.
Before joining Google, I received my Ph.D. in Mathematics at the University of Illinois at Chicago where I was advised by Lev Reyzin and György Turán, and was working on problems in computational complexity theory, combinatorial optimization, and machine learning.
Research Areas
Authored Publications
Sort By
SEMQA: Semi-Extractive Multi-Source Question Answering
Haitian Sun
NAACL (2024) (to appear)
Preview abstract
Recently proposed long-form question answering (QA) systems, supported by large language models (LLMs), have shown promising capabilities. Yet, attributing and verifying their generated abstractive answers can be difficult, and automatically evaluating their accuracy remains an ongoing challenge.
In this paper, we introduce a new QA task for answering multi-answer questions by summarizing multiple diverse sources in a semi-extractive fashion. Specifically, Semi-extractive Multi-source QA (SEMQA) requires models to output a comprehensive answer while mixing between factual quoted spans---copied verbatim from given input sources---and non-factual free-text connectors that glue these spans together into a single cohesive passage. This setting bridges the gap between the outputs of well-grounded but constrained extractive QA systems and more fluent but harder to attribute fully abstractive answers. Particularly, it enables a new mode for language models that leverages their advanced language generation capabilities, while also producing fine in-line attributions by-design that are easy to verify, interpret, and evaluate. To study this task, we create the first dataset of this kind with human-written semi-extractive answers to natural and generated questions, and define text-based evaluation metrics. Experimenting with several LLMs in various settings, we find this task to be surprisingly challenging, demonstrating the importance of our work for developing and studying such consolidation capabilities.
View details
Understanding Generative Retrieval at Scale
Ronak Pradeep
Jimmy Lin
EMNLP 2023
Preview abstract
Popularized by the Differentiable Search Index, the emerging paradigm of Generative Retrieval re-frames the classic information retrieval problem into a sequence-to-sequence modeling task, forgoing external indices and encoding an entire document corpus into the parameters of a single transformer. Although many different approaches have been proposed to improve the effectiveness of generative retrieval, they have only been evaluated on document corpora on the order of 100k in size. We conduct the first study of generative retrieval techniques across various corpus scales, ultimately scaling up to the entire MS MARCO passage ranking task consisting of 8.8M passages. After ablating for the most promising techniques, we then consider model scales up to 11B parameters. Along the way, we uncover several findings about scaling generative retrieval to millions of passages. Notably, the use of synthetic query generation as document representation is the only modeling technique critical to retrieval effectiveness. In addition, we find that the strongest performing architecture modifications from the literature at T5-Base initialization only perform well due to added parameters. Naively scaling to a comparable model size outperforms these proposed techniques. Finally, while model scale is necessary as corpus size increases, we find that given existing techniques, scaling model parameters past a certain point can be detrimental for retrieval effectiveness. This result might be counter-intuitive to the commonly held belief that model capacity is a limiting factor for scaling generative retrieval to larger corpora, and suggests the need for more fundamental improvements. In general, we believe that these findings will be highly valuable for the community to clarify the state of generative retrieval at scale and highlight the challenges currently facing the paradigm.
View details
Automated LOINC Standardization Using Pre-trained Large Language Models
Eric Loreaux
Emma Chesley
Paul Gamble
Martin Seneviratne
Ming-Jun Chen
PMLR (2022), pp. 343-355
Preview abstract
Harmonization of local source concepts to standard clinical terminologies is a prerequisite for multi-center data aggregation and sharing. Challenges in automating the mapping process stem from the idiosyncratic source encoding schemes adopted by different health systems and the lack of large publicly available training data. In this study, we aim to develop a scalable and generalizable machine learning tool to facilitate standardizing laboratory observations to the Logical Observation Identifiers Names and Codes (LOINC). Specifically, we leverage the contextual embedding from pre-trained T5 models and propose a two-stage fine-tuning strategy based on contrastive learning to enable learning in a few-shot setting without manual feature engineering. Our method utilizes unlabeled general LOINC ontology and data augmentation to achieve impressive performance on retrieving the most relevant LOINC targets when limited amount of labeled data are available. We further show that our model generalizes well to unseen targets. Taken together, our approach shows great potential to reduce manual effort in LOINC standardization and can be easily extended to mapping other terminologies.
View details
Instability in clinical risk prediction models using deep learning
Daniel Lopez-Martinez
Alex Yakubovich
Martin Seneviratne
Akshit Tyagi
Ethan Steinberg
N. Lance Downing
Ron C. Li
Keith E. Morse
Nigam H. Shah
Ming-Jun Chen
Proceedings of the 2nd Machine Learning for Health symposium, PMLR (2022), pp. 552-565
Preview abstract
While it has been well known in the ML community that deep learning models suffer from instability, the consequences for healthcare deployments are under-characterised. We study the stability of different model architectures trained on electronic health records, using a set of outpatient prediction tasks as a case study.
We show that repeated training runs of the same deep learning model on the same training data can result in significantly different outcomes at a patient level even though global performance metrics remain stable.
We propose two stability metrics for measuring the effect of randomness of model training, as well as mitigation strategies for improving model stability.
View details
Preview abstract
Multi-Task Learning (MTL) models have shown their robustness, effectiveness, and efficiency for transferring learned knowledge across tasks. In real industrial applications such as web content classification, multiple classification tasks are predicted from the same input text such as a web article. However, at the serving time, the existing multitask transformer models such as prompt or adaptor based approaches need to conduct N forward passes for N tasks with O(N) computation cost. To tackle this problem, we propose a scalable method that can achieve stronger performance with close to O(1) computation cost via only one forward pass. To illustrate real application usage, we release a multitask dataset on news topic and style classification. Our experiments show that our proposed method outperforms strong baselines on both the GLUE benchmark and our news dataset.
View details
Preview abstract
A large majority of American adults get at least some of their news from the Internet. Even though many online news products have the goal of informing their users about the news, they lack scalable and reliable tools for measuring how well they are achieving this goal, and therefore have to resort to noisy proxy metrics (e.g., click-through rates or reading time) to track their performance.
As a first step towards measuring news informedness at a scale, we study the problem of quiz-style multiple-choice question generation, which may be used to survey users about their knowledge of recent news. In particular, we formulate the problem as two sequence-to-sequence tasks: question-answer generation (QAG) and distractor, or incorrect answer, generation (DG). We introduce NewsQuizQA, the first dataset intended for quiz-style question-answer generation, containing 20K human written question-answer pairs from 5K news article summaries. Using this dataset, we propose a series of novel techniques for applying large pre-trained Transformer encoder-decoder models, namely PEGASUS and T5, to the tasks of question-answer generation and distractor generation.
We show that our models outperform strong baselines using both automated metrics and human raters. We provide a case study of running weekly quizzes on real-world users via the Google Surveys platform over the course of two months. We found that users generally found the automatically generated questions to be educational and enjoyable. Finally, to serve the research community, we are releasing the NewsQuizQA dataset.
View details
Preview abstract
We aim to renew interest in a particular multi-document summarization (MDS) task which we call AgreeSum: agreement-oriented multi-document summarization. Given a cluster of articles, the goal is to provide abstractive summaries that represent information common and faithful to all input articles. Given the lack of existing datasets, we create a dataset for AgreeSum, and provide annotations on article-summary entailment relations for a subset of the clusters in the dataset. We aim to create strong baselines for the task by applying the top-performing pretrained single-document summarization model PEGASUS onto AgreeSum, leveraging both annotated clusters by supervised losses, and unannotated clusters by T5-based entailment-related and language-related losses. Compared to other baselines, both automatic evaluation and human evaluation show better article-summary and cluster-summary entailment in generated summaries. On a separate note, we hope that our article-summary entailment annotations contribute to the community's effort in improving abstractive summarization faithfulness.
View details
Investigating Rumor News Using Agreement-Aware Search
Jingbo Shang
Jiaming Shen
Tianhang Sun
Xingbang Liu
Anja Gruenheid
Cong Yu
Jiawei Han
CIKM (2018)
Preview abstract
Recent years have witnessed a widespread increase of rumor news generated by humans and machines in order to attract readership, influence opinions, and increase click-through revenue. Therefore, tools for investigating rumor news have become an urgent necessity. One useful function of such tools is to see ways a specific topic or event is represented by presenting different points of view from multiple sources. In this paper, we propose Maester, a novel agreement-aware search framework for investigating rumor news. Given an investigative question, Maester will retrieve related articles to that question, assign and display top articles from agree, disagree, and discuss categories to users. Splitting the results into these three categories provides the user a holistic view towards the investigative question. We build Maester based on the following two key observations: (1) relatedness can commonly be determined by keywords and entities occurring in both questions and articles, and (2) the level of agreement between the investigative question and the related news article can often be decided by a few key sentences. Accordingly, we use gradient boosting tree models with keyword/entity matching features for relatedness detection, and leverage recurrent neural network to infer the level of agreement. Our experiments on the Fake News Challenge (FNC) “stance detection” dataset demonstrate up to an order of magnitude improvement of Maester over the original FNC winning solution, for agreement-aware search.
View details
