7 papers
LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States
Yeqin Zhang, Yunfei Wang, Jiaxuan Chen +3
Sentence representations are foundational to many Natural Language Processing (NLP) applications. While recent methods leverage Large Language Models (LLMs) to derive sentence repr…
Structures Facilitate Retrieve, Rerank, and Generate
Yeqin Zhang, Haomin Fu, Xujie Zhang +1
Document-grounded dialogue systems (DGDS) utilize knowledge from external documents to answer domain-specific user questions. Existing solutions typically divide documents into ind…
TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models
Yi Zhao, Yajuan Peng, Cam-Tu Nguyen +4
Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but suffer from high inference latency due to autoregressive reasoning.…
LifeBench: A Benchmark for Long-Horizon Multi-Source Memory
Zihao Cheng, Weixin Wang, Yu Zhao +15
Long-term memory is fundamental for personalized agents capable of accumulating knowledge, reasoning over user experiences, and adapting across time. However, existing memory bench…
DSC2025 -- ViHallu Challenge: Detecting Hallucination in Vietnamese LLMs
Anh Thi-Hoang Nguyen, Khanh Quoc Tran, Tin Van Huynh +3
The reliability of large language models (LLMs) in production environments remains significantly constrained by their propensity to generate hallucinations -- fluent, plausible-sou…
Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation
Yeqin Zhang, Yizheng Zhao, Chen Hu +4
Text representation plays a critical role in tasks like clustering, retrieval, and other downstream applications. With the emergence of large language models (LLMs), there is incre…