Anvesh Rao Vijjini

Hi! I am a fifth-year PhD student advised by Prof. Snigdha Chaturvedi at UNC-Chapel Hill. Previously I was working as an NLP Researcher, helping make Bixby, Samsung‘s AI assistant, smarter.

And before that, I was a Computational Linguistics Master's student under the guidance of Prof. Radhika Mamidi with my thesis on Curriculum Learning in Sentiment Analysis at Language Technologies Research Center, IIIT-H.

I like to sketch, bike, origami, and learn new languages in my free time.

CV | | | |

News

[Feb 2025] I am interning at Microsoft Office of Applied Research this summer.
[Jan 2025] Paper accepted at NAACL 2025.
[Oct 2024] Paper accepted at EMNLP 2024 (Findings).
[Oct 2023] Paper accepted at EMNLP 2023 (Findings).
[Apr 2023] I am interning at Bloomberg this summer.
[Jan 2023] Paper accepted at EACL 2023 (Findings).
[Oct 2022] Paper accepted at EMNLP 2022.
[May 2022] I am joining Adobe as a Research Scientist intern for Summer 2022.
[Apr 2021] I will be joining UNC-Chapel Hill as a PhD student in Fall 2021.
[Dec 2020] Paper accepted at EACL 2021.
[Aug 2019] Paper accepted at EMNLP-IJCNLP 2019.
[Jul 2018] Paper accepted at COLING 2018.

Research

My research interests include Alignment, Safety, Personalization and Personas in the context of Large Language Models. Below is a list of my publications, (loosely) organized by these focus areas.

	Personalization and Social Biases I am interested in focusing on the social aspects of AI safety, ensuring that models respect social norms, fairness, and diverse values. I investigated personalization bias in LLMs [1], revealing how models' safety and utility can vary significantly based on the user's identity, impacting the model's performance in ways that disadvantages certain demographics. Additionally, I introduced SocialGaze [2], a multi-step prompting framework to align LLMs' judgments with human social norms by focusing on multiple perspectives. SocialGaze improves model alignment with human judgments while exposing model biases related to gender and age. Relevant Publications: [1] Exploring Safety-Utility Trade-Offs in Personalized Language Models Anvesh Rao Vijjini, Somnath Basu Roy Chowdhury, Snigdha Chaturvedi NAACL, 2025 (oral) [arXiv] [2] SocialGaze: Improving the Integration of Human Social Norms in Large Language Models Anvesh Rao Vijjini, Rakesh R. Menon, Jiyai Fu, Shashank Shrivastava, Snigdha Chaturvedi EMNLP, 2024 (Findings) [arXiv] [anthology] [ppt] [poster] [code-data]
	Narrative Language Understanding and Generation Story Generation has applications in education and interactive learning. I proposed ReLiST [2] for story generation with control over relationships. ReLiST addresses the most important challenge of this task - writing a story coherently while reflecting the given relationships. Relevant Publications: [1] PARROT, a zero-shot approach for enhancing narrative reading comprehension via parallel reading Chao Zhao, Anvesh Rao Vijjini, Snigdha Chaturvedi EMNLP, 2023 (Findings) [link] [2] Towards Inter-character Relationship-driven Story Generation Anvesh Rao Vijjini, Faeze Brahman, Snigdha Chaturvedi EMNLP, 2022 [arXiv] [anthology] [ppt] [poster]
	Efficient Natural Language Processing Efficiency can be achieved in multiple ways; my work explores some of these methods. Curriculum Learning introduces an ordering to the training while using the same model [2]. We have introduced self-normalizing layers within CNN for text classification to achieve better generalization while reducing parameters [4]. I have proposed parameter less decay based weighting layers to weight words closer to aspect terms more than farther ones for Aspect-Based Sentiment Analysis [3]. More recently, I proposed WER-BERT for Automatic WER Estimation, which uses a custom loss function for exploiting the ordinal nature of the WER classification task [1]. I am also interested in distilling models and semi-supervised learning. Relevant Publications: [1] Curricular Next Conversation Prediction Pretraining for Transcript Segmentation Anvesh Rao Vijjini, Hanieh Deilamsalehy, Franck Dernoncourt, Snigdha Chaturvedi EACL, 2023 (Findings) [anthology] [2] WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm Anvesh Rao Vijjini, Akshay Krishna Sheshadri, Sukhdeep Kharbanda EACL, 2021 [arXiv] [anthology] [ppt] [poster] [3] A SentiWordNet Strategy for Curriculum Learning in Sentiment Analysis Anvesh Rao Vijjini, Kaveri Anuranjana, Radhika Mamidi NLDB, 2020 [arXiv] [springer] [ppt] [code] [4] A Position Aware Decay Weighted Network For Aspect Based Sentiment Analysis Avinash Madasu, Anvesh Rao Vijjini NLDB, 2020 [arXiv] [springer] [ppt] [5] Effectiveness of Self Normalizing Neural Networks for Text Classification Avinash Madasu, Anvesh Rao Vijjini CICLing, 2019 [arXiv] [ppt] [poster]
	Model Interpretability Interpreting Machine Learning models is the key to identifying potential challenges and improvements while also moving towards Responsible AI. I have researched and identified the behavior of CNNs, especially what convolutional layers are good at learning and what they are not. To address this, I propose SCARN - a model effectively utilizing recurrent and convolutional structures for text classification [1]. I have also researched and identified when Curriculum Learning (CL) works, especially in sentiment analysis. Using BERT’s attention visualizations, we give qualitative explanations of how CL works; by breaking down a more challenging problem into multiple easier subproblems [2]. Relevant Publications: [1] Sequential Learning of Convolutional Features for Effective Text Classification Avinash Madasu, Anvesh Rao Vijjini EMNLP-IJCNLP, 2019 [arXiv] [anthology] [ppt] [2] Analyzing Curriculum Learning for Sentiment Analysis along Task Difficulty, Pacing and Visualization Axes Anvesh Rao Vijjini, Kaveri Anuranjana, Radhika Mamidi WASSA at EACL, 2021 [arXiv] [anthology] [ppt]
	Robust Natural Language Processing My research at Samsung focused on Domain Adaptation, which helps build models that scale across domains. I have proposed gated convolutional architectures for this problem. The gated mechanism filters out domain-specific information [2]. I further refined this idea to present a Sequential Domain Adaptation framework [1]. I am also interested in exploring Robust NLP for building models that are impervious to noise and are unbiased. Relevant Publications: [1] Sequential Domain Adaptation through Elastic Weight Consolidation for Sentiment Analysis Avinash Madasu, Anvesh Rao Vijjini ICPR, 2020 [arXiv] [ppt] [poster] [2] Gated Convolutional Neural Networks for Domain Adaptation Avinash Madasu, Anvesh Rao Vijjini NLDB, 2019 [arXiv] [springer]
	Resources for Under-Represented Languages Modern machine learning algorithms rely heavily on data, and this reliance has adverse effects in Resource-Scarce Settings. I improved two pre-existing lexicon-based resources in Telugu [3,4,6]. We also created Hindi resources for Question Answering. To aid Educational Applications, we divided the resource into academic grades based on difficulty [5]. While resource creation for scarce languages is essential, hand-curating datasets can be time and labor-intensive. Moving towards Automated Resource Creation, we developed a solution to exploit the massive emoji-rich Social Media presence of Indian languages to automate Multilingual Sentiment Analysis datasets [1]. We also made a linguistically informed rule-based system that relies on semantic roles identified via dependency parsing to convert Hindi sentences into questions to facilitate HindiQA [2]. Relevant Publications: [1] Twitter corpus of Resource-Scarce Languages for Sentiment Analysis and Multilingual Emoji Prediction Nurendra Choudary, Rajat Singh, Anvesh Rao Vijjini, Manish Shrivastava COLING, 2018 [anthology] [data] [2] Hindi Question Generation Using Dependency Structures Anvesh Rao Vijjini, Kaveri Anuranjana, Radhika Mamidi Humanizing AI (HAI) at IJCAI, 2019 [arXiv] [poster] [3] Towards Automation of Sense-type Identification of Verbs in OntoSenseNet Sreekavitha Parupalli, Anvesh Rao Vijjini, Radhika Mamidi SocialNLP at ACL, 2018 [arXiv] [anthology] [4] Towards Enhancing Lexical Resource and Using Sense-annotations of OntoSenseNet for Sentiment Analysis Sreekavitha Parupalli, Anvesh Rao Vijjini, Radhika Mamidi SemDeep-3 at COLING, 2018 [arXiv] [anthology] [code] [5] HindiRC: A Dataset for Reading Comprehension in Hindi Anvesh Rao Vijjini, Kaveri Anuranjana, Radhika Mamidi CICLing, 2019 [researchgate] [poster] [data] [6] BCSAT: A Benchmark Corpus for Sentiment Analysis in Telugu UsingWord-level Annotations Sreekavitha Parupalli, Anvesh Rao Vijjini, Radhika Mamidi Student Research Workshop (SRW) at ACL, 2018 [arXiv] [anthology]

Community Contributions

	Reviewer: ACL 2020, EMNLP 2020, EACL 2021, ACL 2021, EMNLP 2021 Sessions Chair: NLDB 2019
	Teaching Assistant, Natural Language Processing, Monsoon 2016, Dr. Manish Shrivastava Teaching Assistant, Natural Language Processing, Monsoon 2017, Dr. Manish Shrivastava Teaching Assistant, Natural Language Applications, Spring 2017, Dr. Manish Shrivastava

Website design inspired from Jon Barron's website

Personalization and Social Biases

Narrative Language Understanding and Generation

Efficient Natural Language Processing

Model Interpretability

Robust Natural Language Processing

Resources for Under-Represented Languages