AutoVerifier: Automated Verification with Large Language Models
AutoVerifier uses large language models to automate technical claim verification, enhancing accuracy and reliability in scientific research analysis.
Do Audio-Visual Large Language Models Truly See and Hear?
Explore how Audio-Visual Large Language Models integrate audio and visual inputs, revealing challenges in multimodal perception and training biases.
Reducing LLM Biases with Debiasing Direct Preference Optimization
Discover how Debiasing-DPO reduces LLM biases from spurious social contexts, improving accuracy and fairness in high-stakes decision-making.
Controllable RAG Architecture for Accurate Heritage Stories
Explore a novel RAG architecture using competency questions for fact-based cultural heritage storytelling with enhanced accuracy and coherence.
Interpretable Deep RL for Bridge Life-cycle Optimization
Discover interpretable deep reinforcement learning methods for optimizing bridge life-cycle management using element-level condition data.