3 papers
cs.CL2026
LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages
Po-Jen Ko, Che-Cheng Wu, Hung-Chun Hsu +2
Predictive-distribution entropy is a strong answer-selection rule in retrieval-augmented generation (RAG) for question answering: across five QA benchmarks, selecting the answer a…
cs.IR2025
CFDA & CLIP at TREC iKAT 2025: Enhancing Personalized Conversational Search via Query Reformulation and Rank Fusion
Yu-Cheng Chang, Guan-Wei Yeo, Quah Eugene +6
The 2025 TREC Interactive Knowledge Assistance Track (iKAT) featured both interactive and offline submission tasks. The former requires systems to operate under real-time constrain…
cs.IR2025
Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations
Hung-Chun Hsu, Yuan-Ching Kuo, Chao-Han Huck Yang +6
The rapid evolution of e-commerce has exposed the limitations of traditional product retrieval systems in managing complex, multi-turn user interactions. Recent advances in multimo…