Papers by Aparna Garimella

Infogen: Generating Complex Statistical Infographics from Documents (2025.acl-long)

Challenge:	Recent efforts to develop deep learning models for text generation tasks are challenging for non-experts.
Approach:	They propose methods to automatically create deep learning models for extractive and abstractive summarization tasks using large language models.
Outcome:	The proposed methods achieve near state-of-the-art performance on a range of datasets.

Copied to clipboard

Akash Ghosh, Aparna Garimella, Pritika Ramu, Sambaran Bandyopadhyay, Sriparna Saha

Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing (P19-1)

Challenge:	Existing efforts to generate simple charts have focused on generating simple infographics from text-heavy documents.
Approach:	They propose to generate statistical infographics composed of multiple sub-charts that are contextually accurate, insightful, and visually aligned.
Outcome:	The proposed framework outperforms both open-source and closed LLMs in text-to-statistical infographic generation.

Copied to clipboard

Aparna Garimella, Carmen Banea, Dirk Hovy, Rada Mihalcea

Syntactic Text Processing

Challenge:	linguistic studies have shown the prevalence of various lexical and grammatical patterns in texts authored by a person of a particular gender, but models for part-of-speech tagging and dependency parsing have not adapted to account for these differences.
Approach:	They annotate the Wall Street Journal part of the Penn Treebank with the gender information of the articles’ authors and build taggers and parsers trained on this data.
Outcome:	The proposed model can account for gendered differences in syntactic tasks and highlight future venues for developing more accurate taggers and parsers.

Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language Models (2022.emnlp-main)

Copied to clipboard

Aniruddha Mahapatra, Sharmila Reddy Nangi, Aparna Garimella, Anandhavelu N

DocScript: Document-level Script Event Prediction (2024.lrec-main)

Challenge:	Existing methods to perform named entity recognition (NER) on unlabeled data are difficult to obtain in low-resource domains.
Approach:	They propose ways to use unlabeled data for pretraining to improve performance in downstream tasks.
Outcome:	The proposed methods outperform models trained on unlabeled data on seven domains.

Copied to clipboard

Puneet Mathur, Vlad I. Morariu, Aparna Garimella, Franck Dernoncourt, Jiuxiang Gu, Ramit Sawhney, Preslav Nakov, Dinesh Manocha, Rajiv Jain

Reasoning

Challenge:	Existing script event prediction frameworks such as ChatGPT and FlanT5 lack the ability to learn long-range dependencies between events.
Approach:	They propose a novel script event prediction task which aims to predict the next event from a candidate list of narrative events in long-form documents.
Outcome:	The proposed architecture can learn sequential ordering between events at the document scale.

Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents (2025.emnlp-main)

Copied to clipboard

Akriti Jain, Pritika Ramu, Aparna Garimella, Apoorv Saxena

“Judge me by my size (noun), do you?” YodaLib: A Demographic-Aware Humor Generation Framework (2020.coling-main)

Challenge:	Large Language Models have demonstrated strong capabilities in transforming text descriptions or tables to data visualizations . however, it is not straightforward to apply these methods directly for a more real-world use case of visualizing data from long documents .
Approach:	They propose an unsupervised method for generating intent-based charts from documents . they propose an attribution-based metric that uses a structured textual representation of charts .
Outcome:	The proposed method outperforms baselines in terms of chart data accuracy and chart type over baselines.

Copied to clipboard

Aparna Garimella, Carmen Banea, Nabil Hossain, Rada Mihalcea

TabReX: Tabular Referenceless eXplainable Evaluation (2026.acl-long)

Challenge:	Humor is subjective and can be interpreted in different ways by different people.
Approach:	They propose an automatic method for filling the blanks in Mad Libs stories . they build upon the BERT platform to predict location-biased word fillings in incomplete sentences .
Outcome:	The proposed framework outperforms a semi-automated approach for filling the blanks in Mad Libs stories while accounting for the demographic backgrounds of the desired audience.

Copied to clipboard

Tejas Anvekar, Junha Park, Aparna Garimella, Vivek Gupta

“Kelly is a Warm Person, Joseph is a Role Model”: Gender Biases in LLM-Generated Reference Letters (2023.findings-emnlp)

Challenge:	Existing metrics for evaluating the quality of tables generated by large language models flatten tables into text, ignoring structure or relying on fixed references that limit generalization.
Approach:	They propose a reference-less framework for evaluating tabular generation via graph-based reasoning . tabReX converts source text and generated tables into canonical knowledge graphs .
Outcome:	The proposed framework provides a high correlation with expert rankings and stable under harder perturbations.

Copied to clipboard

Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng

Responsible & Trustworthy NLP

Challenge:	Large Language Models (LLMs) are an effective tool to assist individuals in writing documents.
Approach:	They examine gender biases in large language models (LLMs)-generated reference letters . they find that models are biased because they are hallucinated .
Outcome:	The proposed model-generated reference letters are evaluated on 2 popular LLMs- ChatGPT and Alpaca.

SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinement (2024.findings-emnlp)

Copied to clipboard

Ishani Mondal, Zongxia Li, Yufang Hou, Anandhavelu Natarajan, Aparna Garimella, Jordan Boyd-Graber

Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents (2026.acl-long)

Challenge:	Current text-to-image models struggle with generating accurate diagrams from long-context inputs.
Approach:	They propose a task that extracts relevant information from scientific papers and generates diagrams based on user intentions using intermediate code generation.
Outcome:	The proposed task outperforms existing models on factual correctness and visual appeal and outperfies existing ones on automatic and human judgement.

Copied to clipboard

Akriti Jain, Anish Mulay, Divyansh Verma, Aishani Pandey, Pritika Ramu, Aparna Garimella

Challenge:	Existing methods for analyzing information from multiple sources are often too complex or fail to capture nuanced preferences accurately.
Approach:	They propose an interactive decision-making framework that combines document-grounded reasoning with Bayesian preference inference.
Outcome:	The proposed approach outperforms general-purpose LLMs and existing decision-support systems in achieving up to 20% improvement in decision accuracy over strong baselines across domains.

Presentations are not always linear! GNN meets LLM for Text Document-to-Presentation Transformation with Attribution (2024.findings-emnlp)

Copied to clipboard

Himanshu Maheshwari, Sambaran Bandyopadhyay, Aparna Garimella, Anandhavelu Natarajan

Is This a Bad Table? A Closer Look at the Evaluation of Table Generation from Text (2024.emnlp-main)

Challenge:	Existing approaches to generate presentations from document to slide are difficult to implement and cause hallucination.
Approach:	They propose a graph-based solution that uses a combination of graph neural network and LLM to generate a presentation with attribution of content for each slide.
Outcome:	The proposed approach is more efficient than using LLMs for generating a presentation from the text of a document.

Copied to clipboard

Pritika Ramu, Aparna Garimella, Sambaran Bandyopadhyay

Domain-Aware Dependency Parsing for Questions (2021.findings-acl)

Challenge:	Existing measures for table quality evaluation fail to capture the overall semantics of tables . failure to accurately assess table quality can result in including subpar content or overlooking valuable tables in documents.
Approach:	They propose a method that captures table semantics by breaking down a table into atomic statements and comparing them with ground truth statements.
Outcome:	The proposed method shows stronger correlation with human judgments of table quality across four datasets.

Copied to clipboard

Aparna Garimella, Laura Chiticariu, Yunyao Li

Syntactic Text Processing

Challenge:	Pre-trained parsers perform poorly on domain-specific questions, a paper argues . retraining parser with domain- specific questions is expensive, as these require linguistic expertise.
Approach:	They propose an automatic labeled domain question generation framework leveraging domain knowledge and seed domain questions.
Outcome:	The proposed framework improves state-of-the-art parsers on domain questions.

EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction (2021.eacl-main)

Copied to clipboard

Bhanu Prakash Reddy Guda, Aparna Garimella, Niyati Chhaya

AnalystBench: Benchmarking professional long-form report generation with web-mined multimodal tasks (2026.findings-acl)

Challenge:	EmpathBERT is a demographic-aware framework for empathy prediction based on BERT.
Approach:	They propose a demographic-aware framework for empathy prediction based on BERT and utilize user demographics to analyze user responses to stimulative news articles.
Outcome:	The proposed framework surpasses machine learning and deep learning models and highlights the importance of demographic information in the responses.

Copied to clipboard

Chau Minh Pham, Zichao Wang, Puneet Mathur, Alexa Siu, Akriti Jain, Aparna Garimella, Ananya B. Sai, Nedim Lipka, Mohit Iyyer, Varun Manjunatha

LegalCore: A Dataset for Event Coreference Resolution in Legal Documents (2025.findings-acl)

Challenge:	Existing benchmarks decompose the end-to-end professional report generation into individual components.
Approach:	They propose a benchmarking tool that evaluates 20 real-world professional report generation tasks grounded in multimodal document collections.
Outcome:	The proposed model outperforms closed-source models on executive summarization tasks but drops significantly on long-horizon synthesis tasks.

Copied to clipboard

Kangda Wei, Xi Shi, Jonathan Tong, null Sai Ramana Reddy, Anandhavelu Natarajan, Rajiv Jain, Aparna Garimella, Ruihong Huang

Information Extraction & Text Mining

Challenge:	Existing research on event coreference resolution is limited to news articles . existing datasets for news articles are limited to events and coreferences .
Approach:	They present a dataset for the legal domain LegalCore which has been annotated with event and event coreference information.
Outcome:	The legal contract documents annotated in this dataset are several times longer than news articles, with an average length of around 25k tokens per document.

He is very intelligent, she is very beautiful? On Mitigating Social Biases in Language Modelling and Generation (2021.findings-acl)

Copied to clipboard

Aparna Garimella, Akhash Amarnath, Kiran Kumar, Akash Pramod Yalla, Anandhavelu N, Niyati Chhaya, Balaji Vasan Srinivasan

SMART-Editor: A Multi-Agent Framework for Human-Like Design Editing with Structural Integrity (2026.findings-eacl)

Challenge:	Existing studies have focused on mitigating social biases in context-free representations, with recent shift to contextual ones.
Approach:	They propose an approach to mitigate social biases in a large pre-trained contextual language model . they propose lexical co-occurrence-based bias penalization in the decoder units .
Outcome:	The proposed approach reduces biases in fill-in-the-blank sentences and summarizes . it also reduces the biased representations in the frameworks, the authors show .

Copied to clipboard

Ishani Mondal, Meera Bharadwaj, Ayush Roy, Aparna Garimella, Jordan Boyd-Graber

Visual Data in NLP

Challenge:	SMART-EDITOR is a framework for compositional layout and content editing for structured visual domains.
Approach:	They introduce a framework for compositional editing for structured images like posters or websites . SMART-EDITOR maintains global coherence through two complementary strategies .
Outcome:	The proposed framework maintains global coherence through two complementary strategies.

kNN-LM Does Not Improve Open-ended Text Generation (2023.emnlp-main)

Copied to clipboard

Shufan Wang, Yixiao Song, Andrew Drozdov, Aparna Garimella, Varun Manjunatha, Mohit Iyyer

Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness (2024.findings-emnlp)

Challenge:	Interpolation-based retrieval-augmented language models (LMs) are a subtype of retrieval augmented language model that computes the probability of the next token by interpolating between the softmax distribution of the original LM and a token distribution formed by retrieving over an external datastore.
Approach:	They propose to interpolate the predicted distribution of the next word with a distribution formed from the most relevant retrievals for a given prefix.
Outcome:	The proposed methods do not exhibit improvements in open-ended generation quality, as measured by automatic evaluation metrics and human evaluations.

Copied to clipboard

Srija Mukhopadhyay, Adnan Qidwai, Aparna Garimella, Pritika Ramu, Vivek Gupta, Dan Roth

Robustness in NLP

Challenge:	Chart question answering (CQA) is a crucial area of Visual Language Understanding.
Approach:	They evaluate the robustness and consistency of current Visual Language Models on a dataset encompassing diverse question categories and chart formats.
Outcome:	The proposed models handle varying levels of chart and question complexity and are robust across different visual representations of the same underlying data.

ADAPTIVE IE: Investigating the Complementarity of Human-AI Collaboration to Adaptively Extract Information on-the-fly (2025.coling-main)

Copied to clipboard

Ishani Mondal, Michelle Yuan, Anandhavelu N, Aparna Garimella, Francis Ferraro, Andrew Blair-Stanek, Benjamin Van Durme, Jordan Boyd-Graber

Information Extraction & Text Mining

Challenge:	Existing IE systems are either fully supervised, requiring expensive human annotations, or fully unsupervised, extracting information that often do not cater to user’s needs.
Approach:	They propose a framework that uses human-in-the-loop refinement to adapt to changing user questions.
Outcome:	The proposed framework is domain-agnostic, responsive, efficient for helping users access useful information while quickly reorganizing information in response to evolving information needs.

A Neural CRF-based Hierarchical Approach for Linear Text Segmentation (2023.findings-eacl)

Copied to clipboard

Inderjeet Nair, Aparna Garimella, Balaji Vasan Srinivasan, Natwar Modani, Niyati Chhaya, Srikrishna Karanam, Sumit Shekhar

Syntactic Text Processing

Challenge:	Existing methods to segment unformatted text and transcripts explicitly train to predict segment boundaries, but they fail to provide a large annotated dataset.
Approach:	They propose a method to generate hierarchical segmentation structures based on Wikipedia annotations by using a neural conditional random field.
Outcome:	The proposed method outperforms or achieves competitive performance when compared to previous state-of-the-art algorithms.

IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context (2024.naacl-long)

Copied to clipboard

Nihar Sahoo, Pranamya Kulkarni, Arif Ahmad, Tanu Goyal, Narjis Asad, Aparna Garimella, Pushpak Bhattacharyya

DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting (2021.eacl-main)

Challenge:	Existing benchmark datasets focus on English language and the Western context, leaving a void for a reliable dataset that encapsulates India’s unique socio-cultural nuances.
Approach:	They propose to use CrowS-Pairs to create a benchmark dataset that captures and evaluates social biases in Large Language Models (LLMs).
Outcome:	The proposed dataset is available in English and Hindi and leverages LLMs ChatGPT and InstructGPT to augment the existing dataset with diverse societal biases and stereotypes prevalent in India.

Copied to clipboard

Hrituraj Singh, Gaurav Verma, Aparna Garimella, Balaji Vasan Srinivasan

Text Generation

Challenge:	Recent work in this area has focused on author stylized rewriting but is limited by the lack of explicit control of target attributes and being data-driven.
Approach:	They propose a Director-Generator framework to rewrite input text in the target author’s style, specifically focusing on certain target attributes.
Outcome:	The proposed framework has better meaning retention and results in more fluent generations on a small corpus of text authored by three distinct authors.

Demographic-Aware Language Model Fine-tuning as a Bias Mitigation Technique (2022.aacl-short)

Copied to clipboard

Aparna Garimella, Rada Mihalcea, Akhash Amarnath

ClauseRec: A Clause Recommendation Framework for AI-aided Contract Authoring (2021.emnlp-main)

Challenge:	In this paper, we analyze the variations in gender and racial biases in BERT-like language models when exposed to different demographic groups.
Approach:	They analyze gender and racial biases in BERT-like language models when exposed to different demographic groups.
Outcome:	The proposed model can mitigate biases in text authored by disadvantaged demographic groups compared to advantaged groups . the proposed model is agnostic to the language of the speakers behind the language .

Copied to clipboard

Vinay Aggarwal, Aparna Garimella, Balaji Vasan Srinivasan, Anandhavelu N, Rajiv Jain

Information Retrieval

Challenge:	Contracts are a common type of legal document that frequent in business workflows, but there has been limited NLP research in understanding and generating them.
Approach:	They propose a task of clause recommendation to help automate contract authoring . they first predict if a specific clause type is relevant to be added in a contract . then they propose two-staged pipeline to recommend top clauses based on the contract context .
Outcome:	The proposed pipeline predicts if a clause type is relevant to be added in a contract and recommends the top clauses for the given type based on the contract context.

Moneyball with LLMs: Analyzing Tabular Summarization in Sports Narratives (2026.findings-acl)

Copied to clipboard

Ritam Upadhyay, Naman Ahuja, Rishabh Baral, Aparna Garimella, Vivek Gupta