2 citations · 5 across the 12 of their papers we have counts for
13 papers
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…
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…
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…
Retrospex: Language Agent Meets Offline Reinforcement Learning Critic
Yufei Xiang, Yiqun Shen, Yeqin Zhang +1
Large Language Models (LLMs) possess extensive knowledge and commonsense reasoning capabilities, making them valuable for creating powerful agents. However, existing LLM agent fram…
Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization
Shiqi Wang, Yeqin Zhang, Cam-Tu Nguyen
In open-domain Question Answering (QA), dense retrieval is crucial for finding relevant passages for answer generation. Typically, contrastive learning is used to train a retrieval…
Long Short-Term Planning for Conversational Recommendation Systems
Xian Li, Hongguang Shi, Yunfei Wang +3
In Conversational Recommendation Systems (CRS), the central question is how the conversational agent can naturally ask for user preferences and provide suitable recommendations. Ex…
Improving Question Generation with Multi-level Content Planning
Zehua Xia, Qi Gou, Bowen Yu +4
This paper addresses the problem of generating questions from a given context and an answer, specifically focusing on questions that require multi-hop reasoning across an extended…
Revisiting the Role of Similarity and Dissimilarity in Best Counter Argument Retrieval
Hongguang Shi, Shuirong Cao, Cam-Tu Nguyen
This paper studies the task of best counter-argument retrieval given an input argument. Following the definition that the best counter-argument addresses the same aspects as the in…
Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs
Yeqin Zhang, Haomin Fu, Cheng Fu +3
Multi-document grounded dialogue systems (DGDS) belong to a class of conversational agents that answer users' requests by finding supporting knowledge from a collection of document…
Training Keyword Spotting Models on Non-IID Data with Federated Learning
Andrew Hard, Kurt Partridge, Cameron Nguyen +5
We demonstrate that a production-quality keyword-spotting model can be trained on-device using federated learning and achieve comparable false accept and false reject rates to a ce…