Papers by Vivek Gupta

Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents (2025.emnlp-main)

Challenge:	a recent study shows that large language models are limited in their ability to reason over time due to static datasets.
Approach:	They present a dataset that includes 3,971 questions derived from over 14,000 tables . they introduce a template-based question-generation pipeline that harnesses LLMs to refine questions .
Outcome:	The proposed model improves on the TRANSIENTTABLES dataset . it demonstrates that the model can reason over time, even when it is not static .

Copied to clipboard

Manan Suri, Puneet Mathur, Nedim Lipka, Franck Dernoncourt, Ryan A. Rossi, Vivek Gupta, Dinesh Manocha

LLM-Symbolic Integration for Robust Temporal Tabular Reasoning (2025.findings-acl)

Challenge:	Flowcharts are a critical tool for visualizing decision-making processes, but their non-linear structure and complex visual-textual relationships make it difficult to interpret them using LLMs.
Approach:	They propose a task of Fine-grained Flowchart Attribution to trace components grounding a flowchart referring LLM response.
Outcome:	The proposed agent mitigates visual hallucinations in LLM answers over baselines by 10–14% on a FlowExplainBench dataset.

Copied to clipboard

Atharv Kulkarni, Kushagra Dixit, Vivek Srikumar, Dan Roth, Vivek Gupta

Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets (2024.emnlp-main)

Challenge:	Existing methods for temporal tabular question answering are inconsistent and fail to provide the variability needed to thoroughly evaluate models.
Approach:	TEMPTABQA-C uses a synthetic dataset and symbolic representation to generate and execute SQL queries.
Outcome:	TEMPTABQA-C improves on previous methods for temporal tabular question answering . incorporating adaptive fewshot prompting with tailored examples improves performance . lack of robustness, scalability, and interpretable solutions is key obstacle .

Copied to clipboard

Vatsal Gupta, Pranshu Pandya, Tushar Kataria, Vivek Gupta, Dan Roth

Language Models

Challenge:	Language models display sensitivity to input perturbations, causing concerns about trust among users.
Approach:	They propose a methodology to examine how input perturbations affect language models across various scales, including pre-trained models and large language models.
Outcome:	The proposed methods enhance the model’s robustness to input perturbations and if exposure to one perturbation enhances or diminishes its performance with respect to other perturbations.

FlowVQA: Mapping Multimodal Logic in Visual Question Answering with Flowcharts (2024.findings-acl)

Copied to clipboard

Shubhankar Singh, Purvi Chaurasia, Yerram Varun, Pranshu Pandya, Vatsal Gupta, Vivek Gupta, Dan Roth

Enhancing Tabular Reasoning with Pattern Exploiting Training (2022.aacl-main)

Challenge:	Existing benchmarks for visual question answering lack in visual grounding and complexity, particularly in evaluating spatial reasoning skills.
Approach:	They propose to use flowcharts as visual contexts to assess the capabilities of visual question-answering multimodal language models in reasoning.
Outcome:	The proposed benchmarks evaluate models' ability to follow visual information without pre-existing knowledge on a suite of open-source and proprietary multimodal language models using various strategies, followed by an analysis of directional bias.

Copied to clipboard

Abhilash Shankarampeta, Vivek Gupta, Shuo Zhang

Realistic Data Augmentation Framework for Enhancing Tabular Reasoning (2022.findings-emnlp)

Challenge:	Existing methods based on pre-trained language models have shown superior performance over tabular tasks despite showing inherent problems such as not using the right evidence and inconsistent predictions across inputs.
Approach:	They utilize Pattern-Exploiting Training (PET) on pre-trained language models to strengthen tabular reasoning models’ pre-existing knowledge and reasoning abilities.
Outcome:	The proposed model exhibits superior understanding of knowledge facts and tabular reasoning compared to baseline models.

Copied to clipboard

Dibyakanti Kumar, Vivek Gupta, Soumya Sharma, Shuo Zhang

GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning (2025.acl-long)

Challenge:	Existing approaches to constructing training data for Natural Language Inference (NLI) tasks are expensive and time consuming.
Approach:	They propose a semi-automated framework for data augmentation for tabular inference . framework generates hypothesis templates transferable to similar tables . authors say framework could generate human-like tabular examples .
Outcome:	The proposed framework generates human-like tabular inference examples . it is based on human-written constraints and premise paraphrasing .

Copied to clipboard

Shikhhar Siingh, Abhinav Rawat, Chitta Baral, Vivek Gupta

Right for the Right Reason: Evidence Extraction for Trustworthy Tabular Reasoning (2022.acl-long)

Challenge:	Existing methods for analyzing images of events fail to accurately extract contextual meaning from images.
Approach:	They propose a framework to infer global event, temporal, and geospatial information from images . they also introduce a new metric GREAT for a reasoning-weighted evaluation .
Outcome:	The proposed framework enables better understanding of event significance from images . it also shows that meaningful information can be inferred from images, allowing them to be effectively linked to their corresponding events and contextual background.

Copied to clipboard

Vivek Gupta, Shuo Zhang, Alakananda Vempala, Yujie He, Temma Choji, Vivek Srikumar

DIAGRAMS : A Review Framework for Reasoning-Level Attribution in Diagram QA (2026.acl-demo)

Challenge:	Recent studies show that tabular reasoning models use spurious correlations and focus on false evidence or ignore it altogether.
Approach:	They propose a task where models need to extract evidence and then inference labels . they crowdsource evidence row labels and develop unsupervised evidence extraction strategies .
Outcome:	The proposed approach outperforms baseline models on the inference task using only the automatically extracted evidence as the premise.

Copied to clipboard

Anirudh Iyengar Kaniyar Narayana Iyengar, Tampu Ravi Kumar, Manan Suri, Raviteja Bommireddy, Dinesh Manocha, Puneet Mathur, Vivek Gupta

Question Answering

Challenge:	Diagram question answering (Diagram QA) requires reasoning-level attribution that links each question-answer pair to all visual regions needed to derive the answer.
Approach:	They propose a diagram question-answer review framework that decouples interface logic from dataset-specific JSON structures through an internal meta-schema and dataset adapters.
Outcome:	The proposed framework achieves 85.39% precision and 75.30% recall across six diagram QA datasets.

Weaver: Interweaving SQL and LLM for Table Reasoning (2025.emnlp-main)

Copied to clipboard

Rohit Khoja, Devanshu Gupta, Yanjie Fu, Dan Roth, Vivek Gupta

MMTabReal: Real-World Benchmark for Multimodal Table Understanding (2026.findings-acl)

Challenge:	Existing approaches that combine SQL and LLM rely on rigid workflows . Tables play a critical role across various domains such as finance, healthcare and scientific research .
Approach:	Weaver is a modular pipeline that integrates SQL and LLM for table-based question answering.
Outcome:	Weaver outperforms state-of-the-art methods on four Table QA datasets.

Copied to clipboard

Prasham Yatinkumar Titiya, Jainil Trivedi, Chitta Baral, Vivek Gupta

Knowledge-Aware Reasoning over Multimodal Semi-structured Tables (2024.findings-emnlp)

Challenge:	Multimodal tables are ubiquitous in real applications but are difficult to evaluate in multimodal large language models.
Approach:	They propose a multimodal table benchmark that compares 500 real-world tables with 4021 question–answer pairs.
Outcome:	MMtabReal spans four question types, five reasoning categories, and eight structural archetypes.

Copied to clipboard

Suyash Mathur, Jainit Bafna, Kunal Kartik, Harshita Khandelwal, Manish Shrivastava, Vivek Gupta, Mohit Bansal, Dan Roth

Leveraging Data Recasting to Enhance Tabular Reasoning (2022.findings-emnlp)

Challenge:	Existing datasets for tabular question answering focus on text within cells, but real-world data is multimodal, often blending images such as symbols, faces, icons, patterns, and charts with textual content.
Approach:	They propose a dataset to assess whether current AI models can perform knowledge-aware reasoning on multimodal structured data.
Outcome:	The proposed dataset is a robust benchmark for advancing AI’s comprehension and capabilities in analyzing multimodal structured data.

Copied to clipboard

Aashna Jena, Vivek Gupta, Manish Shrivastava, Julian Eisenschlos

TABARD: A Novel Benchmark for Tabular Anomaly Analysis, Reasoning and Detection (2025.findings-emnlp)

Challenge:	Existing approaches to create tabular inference data are limited by human annotation and synthetic generation.
Approach:	They propose a framework for semi-automatically recasting tabular data to make use of both approaches.
Outcome:	The proposed framework can be used to build tabular NLI instances from five datasets.

Copied to clipboard

Manan Roy Choudhury, Anirudh Iyengar Kaniyar Narayana Iyengar, Shikhhar Siingh, Sugeeth Puranam, Vivek Gupta

Unsupervised Semantic Abstractive Summarization (P18-3)

Challenge:	a new benchmark is constructed to evaluate the accuracy of large language models for tabular data . the benchmark uses direct, indirect, and Chain-of-Thought prompting .
Approach:	They propose a framework that uses prompting, self-verification and constraint-based rule execution to improve accuracy.
Outcome:	The proposed framework significantly improves accuracy and recall in tabular data.

Copied to clipboard

Shibhansh Dohare, Vivek Gupta, Harish Karnick

Unbiasing Review Ratings with Tendency Based Collaborative Filtering (2020.aacl-srw)

Challenge:	Existing methods for abstractive summarization are limited in the sense that they can never generate human level summaries for large and complicated documents.
Approach:	They propose a pipeline for automatic abstractive summary generation using co-reference resolution and Meta Nodes.
Outcome:	The proposed pipeline outperforms the state-of-the-art method by 1.7% in node prediction.

Copied to clipboard

Pranshi Yadav, Priya Yadav, Pegah Nokhiz, Vivek Gupta

A Logic-Driven Framework for Consistency of Neural Models (D19-1)

Challenge:	Existing models for rating prediction neglect rating bias due to personal user bias preferences.
Approach:	They propose a tendency-based approach that models the user and item tendency for score prediction along with text review analysis with respect to ratings.
Outcome:	The proposed model minimizes the user and item tendency for score prediction along with text review analysis with respect to ratings.

Copied to clipboard

Tao Li, Vivek Gupta, Maitrey Mehta, Vivek Srikumar

Challenge:	Recent advances in NLP have improved performance on benchmarks such as GLUE . however, tracking performance on a leaderboard is not sufficient to characterize model quality .
Approach:	They propose a framework for constraining neural models using logic rules to regularize them away from inconsistency.
Outcome:	The proposed framework can be used on natural language inference and is compatible with off-the-shelf learning schemes without model redesign.

Enhancing Temporal Understanding in LLMs for Semi-structured Tables (2025.findings-naacl)

Copied to clipboard

Irwin Deng, Kushagra Dixit, Dan Roth, Vivek Gupta

Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data (2023.findings-emnlp)

Challenge:	Temporal reasoning over tabular data presents significant challenges for large language models (LLMs), as evidenced by recent research.
Approach:	They propose a method that enhances LLMs' temporal reasoning over tabular data by using standard prompts and introduce a novel approach, C.L.E.A.R.
Outcome:	The proposed method improves evidence-based reasoning across models and indirect supervision with auxiliary unstructured data significantly boosts model performance in these tasks.

Copied to clipboard

Mubashara Akhtar, Abhilash Shankarampeta, Vivek Gupta, Arpit Patil, Oana Cocarascu, Elena Simperl

Reasoning

Challenge:	Recent benchmarks have assessed language models' numerical abilities . limitations include tokenization and representation of numbers in text, hallucination, and a lack of numerical commonsense knowledge.
Approach:	They propose a hierarchical taxonomy for numerical reasoning skills that includes representation, number sense, manipulation, and complex reasoning.
Outcome:	The proposed model outperforms other models on the tabular Natural Language Inference task.

Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say “I Don’t Know” (2026.findings-acl)

Copied to clipboard

Dhruv Madhwal, Lyuxin David Zhang, Dan Roth, Tomer Wolfson, Vivek Gupta

M-Help: Using Social Media Data to Detect Mental Health Help-Seeking Signals (2025.findings-emnlp)

Challenge:	Large language models struggle to recognize their knowledge limits in closed-book question answering . disagreements between prompting regimes are indicative of potential errors, study finds .
Approach:	They evaluate three task-equivalent prompting regimes: Direct, Assistive, Incremental . disagreements between prompting régimes provide a precise signal of internal uncertainty .
Outcome:	The proposed decomposed prompting outperforms standard uncertainty baselines as an error detector.

Copied to clipboard

Msvpj Sathvik, Zuhair Hasan Shaik, Vivek Gupta

MUTANT: A Multi-sentential Code-mixed Hinglish Dataset (2023.findings-eacl)

Challenge:	Existing datasets for detecting mental health disorders do not identify individuals actively seeking help.
Approach:	This paper introduces a new social media dataset specifically designed to detect help-seeking behavior on social media.
Outcome:	The proposed dataset can detect help-seeking behavior on social media . it can address three key tasks: identifying help- seekkers, diagnosing mental health conditions .

Copied to clipboard

Rahul Gupta, Vivek Srivastava, Mayank Singh

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

Challenge:	Existing methods to identify code-mixed text are difficult to scale effectively and efficiently on multi-sentential data.
Approach:	They propose to identify multi-sentential code-mixed text (MCT) from multilingual articles using a token-level language-aware pipeline.
Outcome:	The proposed dataset includes 67k articles with 85k identified Hinglish MCTs.

Copied to clipboard

Tejas Anvekar, Junha Park, Aparna Garimella, Vivek Gupta

Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness (2024.naacl-long)

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

Ashim Gupta, Rishanth Rajendhran, Nathan Stringham, Vivek Srikumar, Ana Marasovic

Robustness in NLP

Challenge:	Existing approaches to measure robustness are problematic, and out-of-domain evaluations are no longer relevant.
Approach:	They examine models of different sizes spanning different architectural choices and pretraining objectives.
Outcome:	The results show that not all out-of-domain tests provide insight into robustness . merely scaling models does not make them adequately robust .

Bilingual Tabular Inference: A Case Study on Indic Languages (2022.naacl-main)

Copied to clipboard

Chaitanya Agarwal, Vivek Gupta, Anoop Kunchukuttan, Manish Shrivastava

Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression (2024.findings-emnlp)

Challenge:	Existing studies on Tabular Natural Language Inference (TNLI) focus on monolingual settings where tabular premise and hypothesis are in the same language.
Approach:	They propose a task where tabular premise and hypothesis are in two languages . they translate textual hypotheses from an English-indic TNLI dataset into eleven major languages - english and indic .
Outcome:	The proposed model performs well on a bilingual dataset in English and in 11 major Indian languages.

Copied to clipboard

Zhichao Xu, Ashim Gupta, Tao Li, Oliver Bentham, Vivek Srikumar

Language Models

Challenge:	Prior work on compression prioritizes preserving perplexity, which is analogous to training loss.
Approach:	They examine the impact of model compression along four dimensions: degeneration harm, representational harm, dialect bias, and language modeling and downstream task performance.
Outcome:	The proposed compression methods can lead to unexpected consequences, the authors show . quantization preserves bias while pruning degrades quickly.

SumPubMed: Summarization Dataset of PubMed Scientific Articles (2021.acl-srw)

Copied to clipboard

Vivek Gupta, Prerna Bharti, Pegah Nokhiz, Harish Karnick

Text Generation

Challenge:	Existing summarization models that can extract the top few lines of news articles fail to summarize long documents.
Approach:	They constructed a scientific summarization dataset from MEDLINE articles from the PubMed archive to address this problem.
Outcome:	The proposed model outperforms existing models on news article summarization datasets and shows that it is more efficient to extract the top few lines.

INFOTABS: Inference on Tables as Semi-structured Data (2020.acl-main)

Copied to clipboard

Vivek Gupta, Maitrey Mehta, Pegah Nokhiz, Vivek Srikumar

ChartCheck: Explainable Fact-Checking over Real-World Chart Images (2024.findings-acl)

Challenge:	Existing models for text understanding lack human-parity across a wide array of reasoning skills.
Approach:	They propose an extension of the natural language inference task to include semi-structured tabulated text . they propose a semi-structural, multi-domain and heterogeneous nature of the premises that are tables extracted from Wikipedia info-boxes.
Outcome:	The proposed model outperforms baseline models on the GLUE benchmark suite.

Copied to clipboard

Mubashara Akhtar, Nikesh Subedi, Vivek Gupta, Sahar Tahmasebi, Oana Cocarascu, Elena Simperl

Incorporating External Knowledge to Enhance Tabular Reasoning (2021.naacl-main)

Challenge:	Data visualizations are often used to summarize and communicate key information, but they can also be misused to spread misinformation and promote agendas.
Approach:	They propose a dataset for explainable fact-checking against real-world charts that uses vision-language and chart-to-table models to evaluate the validity of the dataset.
Outcome:	The proposed model is based on vision-language and chart-to-table models and proposes a baseline to the community.

Copied to clipboard

J. Neeraja, Vivek Gupta, Vivek Srikumar

REaR : Retrieve, Expand and Refine for Effective Multitable Retrieval (2026.acl-long)

Challenge:	Existing models struggle with tabular inference due to contextualized embeddings of text.
Approach:	They propose easy and effective modifications to how information is presented to a model for tabular inference.
Outcome:	The proposed modifications significantly improve tabular inference performance on large datasets.

Copied to clipboard

Rishita Agarwal, Himanshu Singhal, Peter Baile Chen, Manan Roy Choudhury, Dan Roth, Vivek Gupta

H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables (2025.naacl-long)

Challenge:	REaR is retriever-agnostic and improves dense/ sparse retrievers on complex table QA datasets.
Approach:	a new framework separates semantic relevance from structural joinability for efficient multi-table retrieval. adam scott and eric liu introduce REaR, a three-stage, LLM-free framework.
Outcome:	a new framework improves retrieval quality and performance on complex table QA datasets . it separates semantic relevance from structural joinability and prunes weakly related candidates . the framework is retriever-agnostic and delivers performance competitive with state-of-the-art LLM-augmented retrieval systems .

Copied to clipboard

Nikhil Abhyankar, Vivek Gupta, Dan Roth, Chandan K. Reddy

IndicXNLI: Evaluating Multilingual Inference for Indian Languages (2022.emnlp-main)

Challenge:	Existing methods for tabular reasoning combine textual and symbolic reasoning in a two-stage process to address these limitations.
Approach:	They propose an algorithm that integrates symbolic and semantic (textual) approaches in a two-stage process to address these limitations.
Outcome:	The proposed algorithm outperforms state-of-the-art methods across three tabular question-answering and fact-verification datasets, underscoring its effectiveness and efficiency.

Copied to clipboard

Divyanshu Aggarwal, Vivek Gupta, Anoop Kunchukuttan

Integrity Shield A System for Ethical AI Use & Authorship Transparency in Assessments (2026.eacl-demo)

Challenge:	Indic NLP has made rapid advances in terms of corpora and pre-trained models, but benchmark datasets on standard NLU tasks are limited.
Approach:	They propose to use an NLI dataset for 11 Indic languages to test their accuracy.
Outcome:	The proposed dataset provides useful insights into the behaviour of pre-trained models for a diverse set of languages.

Copied to clipboard

Ashish Raj Shekhar, Shiven Agarwal, Priyanuj Bordoloi, Yash Shah, Tejas Anvekar, Vivek Gupta

Evaluating LLMs’ Mathematical Reasoning in Financial Document Question Answering (2024.findings-acl)

Challenge:	Existing methods for detecting authorship and short answers are ineffective when students query proprietary black-box systems using instructor-provided documents.
Approach:	They propose a document-layer watermarking system that embeds schema-aware, item-level watermarks into assessment PDFs while keeping their human-visible appearance unchanged.
Outcome:	The proposed system achieves high prevention and detection reliability across 30 question papers spanning STEM, humanities, and medical reasoning.

Copied to clipboard

Pragya Srivastava, Manuj Malik, Vivek Gupta, Tanuja Ganu, Dan Roth

Reasoning

Challenge:	Large Language Models excel in natural language understanding, but their capability for complex mathematical reasoning with a hybrid of structured tables and unstructured text remain uncertain.
Approach:	They propose a prompting technique tailored to semi-structured documents that matches or outperforms baselines performance while providing a nuanced understanding of LLMs' abilities.
Outcome:	The proposed prompting technique outperforms baseline prompting techniques while providing a nuanced understanding of LLMs' abilities.

NTSEBENCH: Cognitive Reasoning Benchmark for Vision Language Models (2025.findings-naacl)

Copied to clipboard

Pranshu Pandya, Vatsal Gupta, Agney S Talwarr, Tushar Kataria, Dan Roth, Vivek Gupta

TempTabQA: Temporal Question Answering for Semi-Structured Tables (2023.emnlp-main)

Challenge:	Recent advances in large language models have demonstrated their strong performance on IQ test questions, achieving high scores across many languages.
Approach:	They propose a dataset to evaluate cognitive multimodal reasoning and problem-solving skills of large models.
Outcome:	The proposed dataset contains 2,728 multiple-choice questions and 4,642 images spanning 26 categories.

Copied to clipboard

Vivek Gupta, Pranshu Kandoi, Mahek Vora, Shuo Zhang, Yujie He, Ridho Reinanda, Vivek Srikumar

Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities (2026.findings-eacl)

Challenge:	Semi-structured data often include temporal information about entities, either implicitly or explicitly.
Approach:	They present a dataset that includes 11,454 question-answer pairs from Wikipedia Infobox tables spanning more than 90 distinct domains.
Outcome:	The proposed dataset can be used as a benchmark to improve models for temporal reasoning on semi-structured tables.

Copied to clipboard

Manan Roy Choudhury, Adithya Chandramouli, Mannan Anand, Vivek Gupta

Reasoning

Challenge:	Existing evaluation methods fail to probe fragile reasoning capabilities of large language models (LLMs) a single undetected defect can have catastrophic consequences, highlighting the need for a new class of benchmarks to stress-test their reliability against nuanced contractual flaws.
Approach:	They propose a benchmark to evaluate the fragility of an LLM’s legal reasoning by producing over 7500 real-world perturbed contracts from foundational datasets like CUAD and ContractNLI.
Outcome:	The proposed benchmark evaluates LLMs' ability to detect and reason about fine-grained discrepancies from over 7500 real-world perturbed contracts from foundational datasets like CUAD and ContractNLI.

Map&Make: Schema Guided Text to Table Generation (2025.acl-long)

Copied to clipboard

Naman Ahuja, Fenil Bardoliya, Chitta Baral, Vivek Gupta

TopicBERT for Energy Efficient Document Classification (2020.findings-emnlp)

Challenge:	Existing methods for text-to-table generation overlook what complex information to extract and how to infer it from text.
Approach:	They propose a method that decomposes text into atomic propositions to infer latent schemas.
Outcome:	The proposed method shows significant gains in accuracy and interpretability on three datasets.

Copied to clipboard

Yatin Chaudhary, Pankaj Gupta, Khushbu Saxena, Vivek Kulkarni, Thomas Runkler, Hinrich Schütze

Information Retrieval

Challenge:	Prior work has noted that BERT’s computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissions.
Approach:	They propose to combine topic and language models to optimize the computational cost of fine-tuning for document classification by complementary learning.
Outcome:	The proposed model achieves a 1.4x speedup with 40% reduction in CO2 emission while retaining 99.9% performance over 5 datasets.

Two-Step Classification using Recasted Data for Low Resource Settings (2020.aacl-main)

Copied to clipboard

Shagun Uppal, Vivek Gupta, Avinash Swaminathan, Haimin Zhang, Debanjan Mahata, Rakesh Gosangi, Rajiv Ratn Shah, Amanda Stent

InfoSync: Information Synchronization across Multilingual Semi-structured Tables (2023.findings-acl)

Challenge:	Existing studies on NLP models focus on high resource languages like English, but there are only two datasets for Hindi.
Approach:	They propose a novel two-step classification method which uses textual-entailment predictions for classification task.
Outcome:	The proposed method improves classification performance by using a joint-objective for classification and textual entailment.

Copied to clipboard

Siddharth Khincha, Chelsi Jain, Vivek Gupta, Tushar Kataria, Shuo Zhang

MAPWise: Evaluating Vision-Language Models for Advanced Map Queries (2025.naacl-long)

Challenge:	Information Synchronization of semi-structured data across languages is challenging . culture differences, topic preferences, and editing inconsistency lead to information mismatches .
Approach:	They propose a method for tabular synchronization that uses information from Wikipedia tables in one language with tables in another language.
Outcome:	The proposed method achieves an acceptance rate of 77.28% on Wikipedia . english articles across the web are more timely updated than other languages .

Copied to clipboard

Srija Mukhopadhyay, Abhishek Rajgaria, Prerana Khatiwada, Manish Shrivastava, Dan Roth, Vivek Gupta

Natural Language Interfaces

Challenge:	Vision-language models excel at tasks requiring joint understanding of visual information and natural language.
Approach:	They propose to use choropleth maps to answer questions from three geographical regions in the United States, India, China as question templates.
Outcome:	The proposed model outperforms other models in the area of visual language and visual question answering.

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

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.

Leveraging LLM For Synchronizing Information Across Multilingual Tables (2025.naacl-long)

Copied to clipboard

Siddharth Khincha, Tushar Kataria, Ankita Anand, Dan Roth, Vivek Gupta

Language Models

Challenge:	Recent research has sought to improve cross-language synchronization of Wikipedia tables using rule-based methods, but they struggle with complexity and generalization.
Approach:	They propose to use a dataset to simulate the process of updating outdated Wikipedia tables and introduce a task decomposition strategy that enhances coherence and accuracy.
Outcome:	The proposed model outperforms baselines in Information Updation (1.79%) and Information Addition (20.58%), highlighting its strength in dynamically updating and enriching data across architectures.

Is My Model Using the Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning (2022.tacl-1)

Copied to clipboard

Vivek Gupta, Riyaz A. Bhat, Atreya Ghosal, Manish Shrivastava, Maneesh Singh, Vivek Srikumar

X-Fact: A New Benchmark Dataset for Multilingual Fact Checking (2021.acl-short)

Challenge:	Existing models that claim to reason about evidence should avoid spurious patterns . tabular inputs are well-suited for the study—they admit systematic probes .
Approach:	They propose to use tabular data to test whether models can reason about evidence . they show that a RoBERTa-based model fails to reason on the following counts .
Outcome:	The proposed model fails to reason on tabular data on the following counts . the model is over-sensitive to annotation artifacts and ignores relevant parts of the evidence .

Copied to clipboard

Ashim Gupta, Vivek Srikumar

Federated Retrieval-Augmented Generation: A Systematic Mapping Study (2025.findings-emnlp)

Challenge:	Several fact-checking initiatives, such as PolitiFact, expend manual labor to investigate and determine the truthfulness of viral statements.
Approach:	They propose a multilingual dataset for factual verification of naturally existing claims . they use a benchmark to evaluate the multilingual models .
Outcome:	The proposed model achieves an F-score of around 40%, suggesting it is a challenging benchmark for multilingual fact-checking models.

Copied to clipboard

Abhijit Chakraborty, Chahana Dahal, Vivek Gupta

Information Retrieval

Challenge:	Federated Retrieval-Augmented Generation (Federated RAG) combines Federated Learning (FL) with Retrieleval-augment Generation (RAG)
Approach:	They propose to map literature on Federated Retrieval-Augmented Generation (Federated RAG) this mapping study examines architectural patterns, temporal trends, and key challenges .
Outcome:	The proposed framework improves the factual accuracy of language models by grounding outputs in external knowledge.

Don’t Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text (2023.acl-long)

Copied to clipboard

Ashim Gupta, Carter Blum, Temma Choji, Yingjie Fei, Shalin Shah, Alakananda Vempala, Vivek Srikumar

Robustness in NLP

Challenge:	ATINTER model can be used to rewrite adversarial inputs to make them non-adversarial . if undefended, model should maintain good task performance and effectively mitigate adversarials .
Approach:	They propose a model that intercepts adversarial inputs and learns to rewrite them . they show that it provides better adversarial robustness than existing defense approaches .
Outcome:	The proposed model improves adversarial robustness without compromising task accuracy on a sentiment classification dataset.

FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Use (2026.acl-demo)

Copied to clipboard

Suparno Roy Chowdhury, Tejas Anvekar, Manan Roy Choudhury, Muhammad Ali Khan, Kaneez Zahra Rubab Khakwani, M Bassam Sonbol, Irbaz Bin Riaz, Vivek Gupta

Programming Languages in NLP

Challenge:	Clinical trial databases are central to modern oncology research and drug development.
Approach:	FD-NL2SQL is a schema-aware clinical NL2sql assistant for SQLite-based oncology databases . it decomposes a natural-language question into predicate-level sub-questions and synthesizes executable SQL .
Outcome:	FD-NL2SQL synthesizes SQL based on decomposition, retrieved exemplars, and schema . clinical trial databases are central to modern oncology research and drug development .

TabPert : An Effective Platform for Tabular Perturbation (2021.emnlp-demo)

Copied to clipboard

Nupur Jain, Vivek Gupta, Anshul Rai, Gaurav Kumar

JobMatchAI - An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI (2026.acl-demo)

Challenge:	Current transformers-based models outperform humans on factual evidence evaluation tasks when presented as simple unstructured text.
Approach:	TabPert generates counterfactual data to assess model tabular reasoning issues.
Outcome:	TabPert analyzes the model's shortcomings methodically and quantitatively.

Copied to clipboard

Mayank Vyas, Abhijit Chakraborty, Vivek Gupta

Semantic Text Processing

Challenge:	Recruiters and job seekers rely on search systems to navigate labor markets . many systems fail to handle skill synonyms and nonlinear careers .
Approach:	They propose a production-ready system that integrates Transformer embeddings, skill knowledge graphs, and interpretable reranking.
Outcome:	The proposed system optimizes utility across skill fit, experience, location, salary, and company preferences.

TabXEval: Why this is a Bad Table? An eXhaustive Rubric for Table Evaluation (2025.findings-acl)

Copied to clipboard

Vihang Pancholi, Jainit Sushil Bafna, Tejas Anvekar, Manish Shrivastava, Vivek Gupta

PRAISE: Enhancing Product Descriptions with LLM-Driven Structured Insights (2025.acl-demo)

Challenge:	a rubric-based evaluation framework for tables often overlooks subtle structural and content-level discrepancies.
Approach:	They propose a rubric-based evaluation framework that integrates structural descriptors with contextual signals to enable more precise and consistent table comparison.
Outcome:	The proposed framework is based on a multi-domain benchmark with human annotations and perturbations.

Copied to clipboard

Adnan Qidwai, Srija Mukhopadhyay, Prerana Khatiwada, Dan Roth, Vivek Gupta

Challenge:	Accurate and complete product descriptions are laborious to sift through manually.
Approach:	They propose a system that uses Large Language Models to extract, compare, and structure insights from customer reviews and seller descriptions.
Outcome:	The proposed system can extract, compare, and structure insights from customer reviews and seller descriptions.

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

Corpus for Automatic Structuring of Legal Documents (2022.lrec-1)

Challenge:	Large language model (LLM) approaches to tabular summarization rely on prompt engineering, decomposition pipelines, or entity-level intermediate representations to achieve strong performance.
Approach:	They propose a diagnostic benchmark for long-context tabular summarization using decomposition pipelines and entity-level intermediate representations.
Outcome:	The proposed benchmark improves accuracy and numerical fidelity, but lacks local arithmetic.

Copied to clipboard

Prathamesh Kalamkar, Aman Tiwari, Astha Agarwal, Saurabh Karn, Smita Gupta, Vivek Raghavan, Ashutosh Modi

Summarization

Challenge:	In populous countries, pending legal cases are growing exponentially.
Approach:	They propose a corpus of legal judgment documents in English that is annotated with a label coming from a list of pre-defined rhetorical roles.
Outcome:	The proposed corpus of legal judgment documents is annotated with a label coming from a list of pre-defined rhetorical roles.

Program-of-Thought Reveals LLM Abstraction Ceilings (2026.findings-eacl)

Copied to clipboard

Mike Zhou, Fenil Bardoliya, Vivek Gupta, Dan Roth