Mohit Mayank
Work Projects Research Book Me
ORI - Dynamic LLM Request Routing Intelligence
ORI - Dynamic LLM Request Routing Intelligence

A dynamic framework that leverages multiple LLMs by intelligently routing incoming queries to the most suitable model, improving task-specific accuracy while maintaining efficiency. Outperforms strongest individual models by up to 2.7 points on MMLU and 1.8 points on MuSR.

research-paperlarge-language-modelsroutingmulti-modelarxiv2025

Reinforcement Learning-based Knowledge Graph Reasoning for Explainable Fact-checking
Reinforcement Learning-based Knowledge Graph Reasoning for Explainable Fact-checking

To address the gap in the application of Reinforcement learning (RL) in fact-checking, we propose an RL-based KG reasoning approach for explainable fact-checking.

research-paperreinforcement-learningknowledge-graphfake-news2023

DEAP-FAKED - Knowledge Graph based Approach for Fake News Detection
DEAP-FAKED - Knowledge Graph based Approach for Fake News Detection

A deep neural network based framework to detect fake news from short text by leveraging open domain context using knowledge graphs.

research-paperknowledge-graphfake-news2021

Intrinsic analysis for dual word embedding space models
Intrinsic analysis for dual word embedding space models

Comparative analysis of a total of 84 different word embedding models against semantic, association and analogy evaluation tasks which are made up of 9 open-source linguistics datasets.

research-papernlparxiv2020

with by Mohit Mayank