publications

2025

1. arXiv

   HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance

   Vasu, Rosni, Basu, Chandrayee,  Mishra, Bhavana Dalvi and 3 more authors

   2025

   Abs PDF

   Large Language models have demonstrated promising performance in research ideation across scientific domains. Hypothesis development, the process of generating a highly specific declarative statement connecting a research idea with empirical validation, has received relatively less attention. Existing approaches trivially deploy retrieval augmentation and focus only on the quality of the final output ignoring the underlying reasoning process behind ideation. We present HypER (Hypothesis Generation with Explanation and Reasoning), a small language model (SLM) trained for literature-guided reasoning and evidence-based hypothesis generation. HypER is trained in a multi-task setting to discriminate between valid and invalid scientific reasoning chains in presence of controlled distractions. We find that HypER outperformes the base model, distinguishing valid from invalid reasoning chains (+22% average absolute F1), generates better evidence-grounded hypotheses (0.327 vs. 0.305 base model) with high feasibility and impact as judged by human experts (>3.5 on 5-point Likert scale).

2. HealTAC

   A Large Language Model based Framework for Dementia Related Hypothesis Generation

   Vasu, Rosni, Dong, Hang,  Abdulle, Yusuf and 2 more authors

   In Healthcare Text Analytics Conference Jun 2025

   Abs Poster

3. WWW Companion

   Alan’s Speakeasy - An Ecosystem for the Evaluation of Conversational Agents

   Rossetto, Luca, Sarasua, Cristina,  Inel, Oana and 14 more authors

   In Companion Proceedings of the ACM on Web Conference 2025 Jun 2025

   Abs

   Conversational artificially intelligent agents have received increasing attention in recent years. For many use cases, evaluating such agents requires a human-in-the-loop approach. In this demo paper, we present Alan’s Speakeasy, a Web-based ecosystem for the evaluation of conversational agents.

2024

1. ESWC

   An Extended Evaluation of Single-Label Multi-modal Field of Research Classification Using a Taxonomy-Based Metric

   Ruosch, Florian,  Vasu, Rosni,  Wang, Ruijie and 2 more authors

   In European Semantic Web Conference Jun 2024
2. ISWC

   SciHyp: A Fine-grained Dataset Describing Hypotheses and Their Components from Scientific Articles.

   Vasu, Rosni, Sarasua, Cristina,  and Bernstein, Abraham

   In International Semantic Web Conference Nov 2024

   Abs PDF Code Data

   🏅Received Best Resource Paper Award Nomination🏅

3. NSLP@ESWC

   Single-Label Multi-Modal Field of Research Classification

   Ruosch, Florian,  Vasu, Rosni,  Wang, Ruijie and 2 more authors

   In Natural Scientific Language Processing and Research Knowledge Graphs May 2024

   Abs PDF Code Poster

2023

1. AAAI

   Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Texts.

   Basu, Chandrayee,  Vasu, Rosni,  Yasunaga, Michihiro and 1 more author

   In Association for the Advancement of Artificial Intelligence, AAAI 2023 Feb 2023

   Abs PDF Code Poster

   Automatic medical text simplification can assist providers with patient-friendly communication and make medical texts more accessible, thereby improving health literacy. But curating a quality corpus for this task requires the supervision of medical experts. In this work, we present Med-EASi (Medical dataset for Elaborative and Abstractive Simplification), a uniquely crowdsourced and finely annotated dataset for supervised simplification of short medical texts. Its expert-layman-AI collaborative annotations facilitate controllability over text simplification by marking four kinds of textual transformations: elaboration, replacement, deletion, and insertion. To learn medical text simplification, we fine-tune T5-large with four different styles of input-output combinations, leading to two control-free and two controllable versions of the model. We add two types of controllability into text simplification, by using a multi-angle training approach: position-aware, which uses in-place annotated inputs and outputs, and position-agnostic, where the model only knows the contents to be edited, but not their positions. Our results show that our fine-grained annotations improve learning compared to the unannotated base- line. Furthermore, our position-aware control enhances the model’s ability to generate better simplification than the position-agnostic version. The data and code are available at https://github.com/Chandrayee/CTRL-SIMP.

2022

1. US Patent

   Method and system for generating consent recommendation

   VASU, Rosni KOTTEKULAM, Banahatti, Vijayanand Mahadeo,  and Lodha, Sachin Premsukh

   Feb 2022

   PDF
2. IEEE COMSNETS

   Influence based defense against data poisoning attacks in online learning

   Seetharaman, Sanjay, Malaviya, Shubham,  Vasu, Rosni and 2 more authors

   In 2022 14th International Conference on COMmunication Systems & NETworkS (COMSNETS) Feb 2022

   Abs PDF

   —Data poisoning is a type of adversarial attack on training data where an attacker manipulates a fraction of data to degrade the performance of machine learning model. There are several known defensive mechanisms for handling offline attacks, however defensive measures for online learning, where data points arrive sequentially, have not garnered similar interest. In this work, we propose a defense mechanism to minimize the degradation caused by the poisoned training data on a learner’s model in an online setup. Our proposed method utilizes an influence function which is a classic technique in robust statistics. Further, we supplement it with the existing data sanitization methods for filtering out some of the poisoned data points. We study the effectiveness of our defense mechanism on multiple datasets and across multiple attack strategies against an online learner.

2021

1. US Patent

   Method and system for analyzing unstructured data for compliance enforcement

   Vidhani, Kumar Mansukhlal, Banahatti, Vijayanand Mahadeo,  Lodha, Sachin Premsukh and 8 more authors

   Sep 2021

   PDF
2. HUMAN.AI@AAAI

   Automatic Medical Text Simplification: Challenges of Data Quality and Curation.

   Basu, Chandrayee,  Vasu, Rosni,  Yasunaga, Michihiro and 2 more authors

   In Human Partnership with Medical Artificial Intelligence (HUMAN.AI) ), AAAI Fall 2021 Symposium Nov 2021

   Abs PDF

   Health Literacy is the degree to which individuals can comprehend basic health information needed to make appropriate health decisions. The topmost reason for low health literacy is the vocabulary gap between providers and patients. Automatic medical text simplification can contribute to improving health literacy by assisting providers with patientfriendly communication, improving health data search, and making online medical texts more accessible. It is, however, extremely challenging to curate quality corpus for this natural language processing (NLP) task. In this position paper, we observe that, despite recent research efforts, existing open corpora for medical text simplification are poor in quality and size. In order to match the progress in general text simplification and style transfer, we must leverage careful crowdsourcing. We discuss the challenges of naive crowd-sourcing. We propose that careful crowd-sourcing for medical text simplification is possible, when combined with automatic data labeling, a well-designed expert-layman collaboration framework, and context-dependent crowd-sourcing instructions.

3. arXiv

   Gradient-based Data Subversion Attack Against Binary Classifiers

   Vasu, Rosni K, Seetharaman, Sanjay,  Malaviya, Shubham and 2 more authors

   Nov 2021

   Abs PDF

   Machine learning based data-driven technologies have shown impressive performances in a variety of application domains. Most enterprises use data from multiple sources to provide quality applications. The reliability of the external data sources raises concerns for the security of the machine learning techniques adopted. An attacker can tamper the training or test datasets to subvert the predictions of models generated by these techniques. Data poisoning is one such attack wherein the attacker tries to degrade the performance of a classifier by manipulating the training data. In this work, we focus on label contamination attack in which an attacker poisons the labels of data to compromise the functionality of the system. We develop Gradient-based Data Subversion strategies to achieve model degradation under the assumption that the attacker has limited knowledge of the victim model. We exploit the gradients of a differentiable convex loss function (residual errors) with respect to the predicted label as a warm-start and formulate different strategies to find a set of data instances to contaminate. Further, we analyze the transferability of attacks and the susceptibility of binary classifiers. Our experiments show that the proposed approach outperforms the baselines and is computationally efficient.

2020

2019

1. PAL@AAAI

   Consent Recommender System: A Case Study on LinkedIn Settings

   Rosni, KV, Shukla, Manish,  Banahatti, Vijayanand and 1 more author

   In PAL: Privacy-Enhancing Artificial Intelligence and Language Technologies at AAAI Spring Symposium Mar 2019

   Abs PDF

   Privacy is an increasing concern in the digital world, especially when it has become a common knowledge that even high profile enterprises process data without data-subject’s consent. In certain cases where data-subject’s consent was taken, it was not linked to the proper purpose of processing. To address this growing concern, newer privacy regulations and laws are emerging to empower a data-subject with informed and explicit consent through which she can allow or revoke usage of her personal data. However, it has been shown that privacy self-management does not provide the expected results. This is mainly due to information overload as data-subjects use multiple services entailing variety of purposes, and hence, resulting in a very large number of consent requests. This may lead to consent fatigue as data-subject is now expected to provide informed consent for each associated purpose. The consent fatigue in data-subjects can lead to either incorrect decision making or opting for default values provided by the enterprise, and thus, defeating the purpose of new data privacy regulations. In this work, we discuss the factors influencing the informed consent of a data-subject. Further, we propose a ‘consent recommender system’ based on Factorization Machines (FMs) to assist the data-subject and thereby avoiding consent fatigue. Our consent recommender system effectively models the interaction between the different factors which influence a data-subject’s informed consent. We discuss how this setup extends for cold start data-subjects facing the decision problem with consent requests from multiple enterprises. Additionally, we demonstrate the scenario of consent recommendation as a prediction problem with minimum attributes available from LinkedIn’s privacy settings.

2018

2017

1. RecSysKTL

   Divide and Transfer: Understanding Latent Factors for Recommendation Tasks.

   Rao, Vidyadhar, Rosni, KV,  and Padmanabhan, Vineet

   In RecSysKTL Workshop co-located with ACM RecSys Aug 2017

   Abs PDF

   Traditionally, latent factor models have been the most successful techniques to build recommendation systems. While the key is to capture the user interests effectively, most research is focused on learning latent factors under cold-start and data sparsity situations. Our work brings a complementary approach to the previous studies showing that understanding the semantic aspects of latent factors could give a hint on how to transfer useful knowledge from auxiliary domain(s) to the target domain. In this work, we propose a collaborative filtering technique that can effectively utilize the user preferences and content information. In our approach, we follow a divide and transfer strategy that could derive semantically meaningful latent factors and utilize only the appropriate components for recommendations. We demonstrate the effectiveness of our approach due to improved latent feature space in both single and cross-domain tasks. Further, we also show its robustness by performing extensive experiments under cold-start and data sparsity contexts.