Papers by Mohit Gupta

11 papers
FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent work improving LLM math reasoning with synthetic data uses unique setups, making comparison of data synthesis strategies impractical.
Approach: They propose a framework for LLM assessment of math reasoning with synthetic data . they use 10 existing data synthesis strategies and multiple other factors to study performance .
Outcome: The proposed data synthesis strategies outperform public datasets on OlympiadBench, CollegeMath, GSMPlus and MATH.
Can Sequence-to-Sequence Transformers Naturally Understand Sequential Instructions? (2023.starsem-1)

Copied to clipboard

Challenge: Using a limited annotation budget, we can greatly improve the performance on intermediate steps with a drop in final-step performance.
Approach: They propose to use a pre-supervised sequence-to-sequence transformer to provide training signals on intermediate steps with zero gold supervision instead of only final-step supervision to improve performance.
Outcome: The proposed model significantly improves on intermediate steps with a drop in final-step performance on one subtask, but also shows decreased performance on another subtask.
GRAVL-BERT: Graphical Visual-Linguistic Representations for Multimodal Coreference Resolution (2022.coling-1)

Copied to clipboard

Challenge: Multimodal coreference resolution (MCR) is a crucial capability for building next-generation conversational agents.
Approach: They propose a multimodal coreference resolution model that resolves coreferences made in multi-turn dialogues with scene images.
Outcome: The proposed model resolves coreferences made in multi-turn dialogues with scene images.
Med-CoDE: Medical Critique based Disagreement Evaluation Framework (2025.naacl-srw)

Copied to clipboard

Challenge: Existing evaluation methods for large language models lack robustness and accuracy in medical contexts.
Approach: They propose an evaluation framework for medical LLMs that measures disagreement between model-generated responses and established medical ground truths.
Outcome: The proposed evaluation framework captures accuracy and reliability in medical settings.
Knowledge-Aware Reasoning over Multimodal Semi-structured Tables (2024.findings-emnlp)

Copied to clipboard

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.
AbuseAnalyzer: Abuse Detection, Severity and Target Prediction for Gab Posts (2020.coling-main)

Copied to clipboard

Challenge: Existing studies on estimating the severity of abuse and the target of online abuse have focused on detecting and curtailment of such types of abuse.
Approach: They propose to analyze online abuse from the perspective of presence, severity and target of abusive behavior from 7,601 posts from Gab and to estimate the severity of abuse.
Outcome: The proposed system achieves 80% accuracy for abuse presence, 82% accuracy for abusive target prediction, and 65% accuracy for severity prediction.
ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution (2023.findings-eacl)

Copied to clipboard

Challenge: Existing datasets vary in definition of coreferences and are curated for linguistic experts.
Approach: They propose to use ezCoref to create a crowdsourcing-friendly coreference annotation methodology that teaches annotators only cases that are treated similarly across existing datasets.
Outcome: The proposed method reannotates 240 passages from seven existing english coreference datasets while teaching annotators only cases that are treated similarly across them.
Image Manipulation via Multi-Hop Instructions - A New Dataset and Weakly-Supervised Neuro-Symbolic Approach (2023.emnlp-main)

Copied to clipboard

Challenge: Recent studies have shown that neuro-symbolic models lack interpretability and are not robust to noise.
Approach: They propose to extend Neuro Symbolic Concept Learning (NSCL) which has been quite effective for the task of Visual Question Answering (VQA) they create a new dataset for the image manipulation task and demonstrate that NeuroSIM is highly competitive with or beats SOTA baselines that make use of supervised data for manipulation.
Outcome: The proposed system performs complex multi-hop reasoning over multi-object scenes and only requires weak supervision in the form of annotated data for VQA.
Semantic Parsing for Task Oriented Dialog using Hierarchical Representations (D18-1)

Copied to clipboard

Challenge: Existing work on task oriented dialog systems has limited expressive power to one intent per query and one slot label per token.
Approach: They propose a hierarchical annotation scheme for semantic parsing that allows representation of compositional queries.
Outcome: The proposed representation outperforms sequence-to-sequence approaches on a 44k annotated query dataset.
Prompting Vision-Language Models For Aspect-Controlled Generation of Referring Expressions (2024.findings-naacl)

Copied to clipboard

Challenge: Referring Expression Generation (REG) is the task of generating a descriptive caption that uniquely identifies a given target in the scene.
Approach: They propose an Aspect-Controlled REG task which requires generating a referring expression conditioned on the input aspect(s) by changing the input input such as color, location, action etc.
Outcome: The proposed model beats all prior works in the CIDEr score and achieves comparable performance to training with 100% of real data.
DEMETR: Diagnosing Evaluation Metrics for Translation (2022.emnlp-main)

Copied to clipboard

Challenge: BLEU scores are based on string overlap, but they are opaque in comparison to newer learned metrics.
Approach: They propose a dataset to evaluate MT evaluation metrics based on linguistic perturbations in English . they find learned metrics perform substantially better than string-based metrics .
Outcome: The proposed dataset shows that learned metrics perform better than string-based metrics . the dataset contains 31K English examples that cover 35 different linguistic phenomena .

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