Papers by Vijjini Anvesh Rao

8 papers
Towards Inter-character Relationship-driven Story Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Recent story generation methods can generate stories based on open-ended prompts and planners but can neither encode character relationships nor give explicit control over the characters and their relationships.
Approach: They propose a model that uses relationships as latent variables for story generation and propose 'relationship-driven' story generation.
Outcome: The proposed model generates stories sentence by sentence with relationships that are more faithful to desired relationships while maintaining the content quality.
Curricular Next Conversation Prediction Pretraining for Transcript Segmentation (2023.findings-eacl)

Copied to clipboard

Challenge: Prior research on document segmentation has focused on segmenting documents such as Wikipedia articles.
Approach: They propose to pretrain a model to identify consecutive conversations to address these challenges . they introduce a curriculum to Advanced NCP to make the task more relevant to the downstream task .
Outcome: The proposed model outperforms previous models in speech recognition errors and is robust to speech recognition.
Sequential Learning of Convolutional Features for Effective Text Classification (D19-1)

Copied to clipboard

Challenge: Existing models for text classification have largely ignored convolution filters and max pooling . text classification is one of the major applications of natural language processing .
Approach: They propose a convolutional attentive recurrent network model which uses convolution filters and max pooling to improve text classification.
Outcome: The proposed model outperforms existing convolutional models on text classification tasks.
SocialGaze: Improving the Integration of Human Social Norms in Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Increasingly, large language models (LLMs) are able to understand and rationalize socially acceptable behaviors, but they are often misaligned with human consensus.
Approach: They propose a multi-step prompting framework that verbalizes a social situation from multiple perspectives before forming a judgment.
Outcome: The proposed framework improves the alignment with human judgments by up to 11 F1 points with the GPT-3.5 model.
Exploring Safety-Utility Trade-Offs in Personalized Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Prior studies have shown that large language models can exhibit bias against specific demographic groups and engage in the generation of stereotypical responses.
Approach: They propose a framework to evaluate LLM performance along two axes: safety and utility.
Outcome: The proposed framework evaluates the performance of LLMs along two axes: safety and utility.
Twitter corpus of Resource-Scarce Languages for Sentiment Analysis and Multilingual Emoji Prediction (C18-1)

Copied to clipboard

Challenge: a majority of research studies on twitter focus on English tweets, despite the fact that English dominates the mix of languages.
Approach: They leverage social media platforms such as twitter for developing corpus across multiple languages . they use tweets to collect data for sentiment analysis and emoji prediction .
Outcome: The proposed method is applicable for resource-scarce languages provided speakers of that particular language are active users on social media platforms.
Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations? (2026.acl-long)

Copied to clipboard

Challenge: Power differences shape human communication through well-documented socio-cognitive effects . asymmetric relationships or power differentials give rise to well-known socio-computational effects - lianelli, 1976 .
Approach: They simulate multi-turn, power-asymmetric dialogues with personas from diverse professions . they find that LLMs show key socio-cognitive effects of power, albeit with nuances and variability .
Outcome: The results show that large language models exhibit socio-cognitive effects of power . the results are consistent with previous studies on LLMs .
BCSAT : A Benchmark Corpus for Sentiment Analysis in Telugu Using Word-level Annotations (P18-3)

Copied to clipboard

Challenge: Existing sentiment analysis systems have a lot of scope for improvement to meet the standards of the end users.
Approach: They propose to generate a systematically annotated corpus that can support sentiment analysis tasks in Telugu using word-level sentiment annotations.
Outcome: The proposed resource can be used to improve sentiment analysis tasks in Telugu using word-level sentiment annotations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations