Papers by Kartik Sharma
OG-RAG: Ontology-grounded retrieval-augmented generation for large language models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing retrieval-augmented models fail to account for structured domain knowledge, leading to suboptimal context generation. |
| Approach: | They propose an Ontology-Grounded Retrieval Augmented Generation method to enhance LLM-generated responses by anchoring retrieval processes in domain-specific ontologies. |
| Outcome: | The proposed method increases recall of accurate facts by 55% and improves response correctness by 40% across four different LLMs. |
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) extends large language models with external knowledge, but it must balance limited effective context, redundant retrieved evidence, and the loss of fine-grained facts. |
| Approach: | They propose a hybrid RAG framework that uses natural-language snippets and semantic compression vectors to preserve passages in text form and compress remaining evidence into interpretable vectors for iterative evidence reranking. |
| Outcome: | The proposed framework improves answer relevance, answer correctness and semantic similarity across 9 datasets and 5 open-source LLMs. |
Cross-Modal Projection in Multimodal LLMs Doesn’t Really Project Visual Attributes to Textual Space (2024.acl-short)
Copied to clipboard
| Challenge: | Existing multimodal large language models are limited to general-purpose multimodal tasks like question-answering on natural images. |
| Approach: | They propose to use cross-modal projection networks and a large language model to model domain-specific visual attributes of MLLMs. |
| Outcome: | The proposed models gain domain-specific visual capabilities when the projection is fine-tuned, but the updates do not extract relevant domain-specific visual attributes. |
Who Speaks Matters: Analysing the Influence of the Speaker’s Linguistic Identity on Hate Classification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models are known to be brittle and biased against marginalised communities and dialects. |
| Approach: | They investigate the robustness of hate speech classification using LLMs when explicit and implicit markers of the speaker’s ethnicity are injected into the input. |
| Outcome: | The proposed model is robust when explicit and implicit markers of speaker's ethnicity are injected into the input. |