Publications

2025

SemEval-2025

VerbaNexAI at SemEval-2025 Task 3: Fact Retrieval with Google Snippets for LLM Context Filtering to identify Hallucinations

LLM chain-of-thought prompting with Google snippet retrieval versus classical NLP span detection for SemEval-2025 Task 3 (Mu-SHROOM, English).

• Natural Language Processing
• Large Language Models
• Hallucination Detection
• RAG

2025

IEEE C3 2025

PubMed API and LLM-Driven Hybrid Retrieval System for Biomedical Question Answering

Resource-efficient biomedical QA combining LLM key-term extraction, weirdness scoring, PubMed API retrieval, and RAG with Qwen3-30B-A3B on BioASQ.

• Biomedical Question Answering
• Information Retrieval
• Large Language Models
• PubMed API

2024

SemEval-2024

VerbaNexAI Lab at SemEval-2024 Task 1: A Multilayer Artificial Intelligence Model for Semantic Relationship Detection

Four-layer feature extraction with LSTM embeddings and ensemble regressors for semantic textual relatedness (SemEval-2024 Task 1, English).

• Natural Language Processing
• Semantic Textual Relatedness
• Deep Learning
• LSTM

2023

SemEval-2023

UTB-NLP at SemEval-2023 Task 3: Weirdness, Lexical Features for Detecting Categorical Framings, and Persuasion in Online News

Lexical weirdness and linguistic features for news genre and framing detection in SemEval-2023 Task 3 (English).

• Natural Language Processing
• Persuasion Detection
• Lexical Features
• News Classification