4 papers
EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
Yilong Li, Suman Banerjee, Tong Che
Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the s…
LLMs as Architects and Critics for Multi-Source Opinion Summarization
Anuj Attri, Arnav Attri, Pushpak Bhattacharyya +4
Multi-source Opinion Summarization (M-OS) extends beyond traditional opinion summarization by incorporating additional sources of product metadata such as descriptions, key feature…
"This Suits You the Best": Query Focused Comparative Explainable Summarization
Arnav Attri, Anuj Attri, Pushpak Bhattacharyya +4
Product recommendations inherently involve comparisons, yet traditional opinion summarization often fails to provide holistic comparative insights. We propose the novel task of gen…
Why We Feel What We Feel: Joint Detection of Emotions and Their Opinion Triggers in E-commerce
Arnav Attri, Anuj Attri, Pushpak Bhattacharyya +4
Customer reviews on e-commerce platforms capture critical affective signals that drive purchasing decisions. However, no existing research has explored the joint task of emotion de…