6 citations · 7 across the 5 of their papers we have counts for
7 papers
Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency
Wenhan Yu, Wenxin Wu, Hao Wang +1
Factual hallucination is commonly defined by incorrect factual outputs. We study a paraphrase-induced hallucination setting, where a model answers a factual question correctly in i…
JustMem: Just-Enough Memory Access for Long-Term Conversations
Guanhua Chen, Yanting Wang, Wenjing Zhi +1
Efficient long-term conversational memory requires retrieving sufficient evidence without indiscriminately expanding the context presented to the language model. This is challengin…
Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models
Wenhan Yu, Xinbo Lin, Lanxin Ni +2
Large language models (LLMs) have demonstrated strong reasoning abilities across specialized domains, motivating research into their application to legal reasoning. However, existi…
SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning
Wenhan Yu, Zhaoxi Zhang, Wang Chen +5
Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challengin…
CMRAG: Co-modality-based visual document retrieval and question answering
Wang Chen, Wenhan Yu, Guanqiang Qi +5
Retrieval-Augmented Generation (RAG) has become a core paradigm in document question answering tasks. However, existing methods have limitations when dealing with multimodal docume…
HSF: Defending against Jailbreak Attacks with Hidden State Filtering
Cheng Qian, Hainan Zhang, Lei Sha +1
With the growing deployment of LLMs in daily applications like chatbots and content generation, efforts to ensure outputs align with human values and avoid harmful content have int…
Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generation
Guanhua Chen, Wenhan Yu, Xiao Lu +3
While Retrieval-Augmented Generation (RAG) plays a crucial role in the application of Large Language Models (LLMs), existing retrieval methods in knowledge-dense domains like law a…