Papers by Dhruv Agarwal

4 papers
Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA (2024.findings-naacl)

Copied to clipboard

Challenge: a universal question-answering system that can operate on any knowledge graph is presented . previous work that relied on training data to query structured data stores is unrealistic .
Approach: They propose a universal question-answering system that can operate on any knowledge graph . they use an LLM-backed symbolic agent to generate query-program exemplars .
Outcome: The proposed system outperforms state-of-the-art model on domain-specific KGs by 7.08 F1 . the proposed system can be ready to use within a day, the authors show .
Entity Linking via Explicit Mention-Mention Coreference Modeling (2022.naacl-main)

Copied to clipboard

Challenge: Using a learning approach for entity mentions is a key component of modern entity linking systems for both candidate generation and making linking predictions.
Approach: They propose a training approach that builds minimum spanning arborescences over mentions and entities to explicitly model mention coreference relationships.
Outcome: The proposed approach improves candidate generation recall and link accuracy on the biomedical dataset and on MedMentions, setting a new SOTA result in linking accuracy.
Machine Reading Comprehension using Case-based Reasoning (2023.findings-emnlp)

Copied to clipboard

Challenge: Current state-of-the-art machine readers do not support case-based reasoning .
Approach: They propose a method that extracts a set of similar cases from a nonparametric memory and then predicts an answer by selecting the span in the test context that is most similar to the contextualized representations of answers.
Outcome: The proposed method outperforms baselines on NaturalQuestions and NewsQA by 11.5 and 8.4 EM.
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