LiCQA : A Lightweight Complex Question Answering System

Research Summary

Contribution Summary

• Over the last twenty years, significant progress has been made in designing and implementing Question Answering (QA) systems.
• However, addressing complex questions, the answers to which are spread across multiple documents, remains a challenging problem.
• Recent QA systems that are designed to handle complex questions work either on the basis of knowledge graphs, or utilise contem- porary neural models that are expensive to train, in terms of both computational resources and the volume of tr

Why It Matters For Eval

• The results of our experiments show that LiCQA significantly outperforms these two state-of-the-art systems on benchmark data with noteworthy reduction in latency.

Related Papers

• Toward LLM-Supported Automated Assessment of Critical Thinking Subskills Embedding Neighbor
• SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning Embedding Neighbor
• HebID: Detecting Social Identities in Hebrew-language Political Text Embedding Neighbor
• Cognitive networks reconstruct mindsets about STEM subjects and educational contexts in almost 1000 high-schoolers, University students and LLM-based digital twins Embedding Neighbor
• Uncovering Grounding IDs: How External Cues Shape Multimodal Binding Embedding Neighbor
• BOOM: Beyond Only One Modality KIT's Multimodal Multilingual Lecture Companion Embedding Neighbor
• Should We Still Pretrain Encoders with Masked Language Modeling? Embedding Neighbor
• CitiLink-Summ: Summarization of Discussion Subjects in European Portuguese Municipal Meeting Minutes Embedding Neighbor
• Probabilistic distances-based hallucination detection in LLMs with RAG Embedding Neighbor
• The Headless Firm: How AI Reshapes Enterprise Boundaries Tag Overlap
• Measuring AI Ability to Complete Long Software Tasks Tag Overlap
• Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers Tag Overlap