Papers by Rituraj Singh

5 papers
NLMs: Augmenting Negation in Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Negation is the fundamental component in a natural language that reverses the semantic meaning of a sentence.
Approach: They propose a language model objective with a weighted cross-entropy loss and elastic weight consolidation regularization to improve negation understanding.
Outcome: The proposed model reduces the error rate of the existing models by 8% and outperforms them on original and negation benchmarks.
Constructing A Dataset of Support and Attack Relations in Legal Arguments in Court Judgements using Linguistic Rules (2022.lrec-1)

Copied to clipboard

Challenge: Argumentation mining is a growing area of research with several interesting practical applications.
Approach: They propose three sets of rules based on linguistic knowledge and distant supervision to identify such relations from Indian Supreme Court judgments.
Outcome: The proposed rules are based on linguistic knowledge and distant supervision and use the source of the argument to build a dataset of Support and Attack relations between sentences in a court judgement with reasonable accuracy.
RG-VQA: Leveraging Retriever-Generator Pipelines for Knowledge Intensive Visual Question Answering (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to improve the reasoning capabilities of VQA systems are limited due to complexity of graph neural networks and end-to-end training.
Approach: They propose a method to integrate Dense Passage Retrievers with Vision Language Models to boost the reasoning capabilities of VQA systems.
Outcome: The proposed method outperforms human accuracy and GPT-4 in the ScienceQA dataset.
From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding (2025.findings-acl)

Copied to clipboard

Challenge: Accurately grounding visual and textual elements within mobile user interfaces remains a challenge for Vision-Language Models (VLMs).
Approach: They propose a mobile UI understanding model trained on a dataset specifically tailored for mobile screen understanding and grounding.
Outcome: The proposed model achieves significant gains in accuracy across all perception tasks and on reasoning benchmarks.
Nanda Family: Open-Weights Generative Large Language Models for Hindi (2026.eacl-long)

Copied to clipboard

Challenge: Large language models remain predominantly English-centric, which limits their utility for underrepresented languages.
Approach: They propose to extend Llama’s vocabulary with 20% Hindi-specific tokens, thus halving Hindi tokenization fertility while preserving English efficiency.
Outcome: The proposed models outperform open-weight models of comparable size on a 65B-token corpus and bilingual instruction and safety alignment on . a culturally grounded dataset.

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