4 papers
Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale
Chinmay Soni, Shivam Chourasia, Gaurav Kumar +1
Applying large, proprietary API-based language models to text-to-SQL tasks poses a significant industry challenge: reliance on massive, schema-heavy prompts results in prohibitive…
Entailed Opinion Matters: Improving the Fact-Checking Performance of Language Models by Relying on their Entailment Ability
Gaurav Kumar, Ayush Garg, Debajyoti Mazumder +3
Automated fact-checking has been a challenging task for the research community. Prior work has explored various strategies, such as end-to-end training, retrieval-augmented generat…
MultiCheck: Strengthening Web Trust with Unified Multimodal Fact Verification
Aditya Kishore, Gaurav Kumar, Jasabanta Patro
Misinformation on the web increasingly appears in multimodal forms, combining text, images, and OCR-rendered content in ways that amplify harm to public trust and vulnerable commun…
Model-First Reasoning LLM Agents: Reducing Hallucinations through Explicit Problem Modeling
Annu Rana, Gaurav Kumar
Large Language Models (LLMs) often struggle with complex multi-step planning tasks, showing high rates of constraint violations and inconsistent solutions. Existing strategies such…