Jianpeng Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianpeng Hu has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Jialun Zhong
Wangxuan Institute of Computer Technology Peking University Beijing China
1 shared publication - Lei Zou
Peking University, Beijing, China
1 shared publication - Wenfa Qi
Wangxuan Institute of Computer Technology, Peking University, Beijing 100871, China
1 shared publication - Yanzeng Li
Beijing Normal University
1 shared publication
Latest Publications
- Open Access
Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph
The Retrieval-augmented generation (RAG) system based on Large language model (LLM) has made significant progress. It can effectively reduce factuality hallucinations, but faithfulness hallucinations still exist. Previous methods for detecting faithfulness hallucinations either neglect to capture the models' internal reasoning processes or handle those features coarsely, making it difficult for discriminators to learn. This paper proposes a semantic-level internal reasoning graph-based method for detecting faithfulness hallucination. Specifically, we first extend the layer-wise relevance propagation algorithm from the token level to the semantic level, constructing an internal reasoning graph based on attribution vectors. This provides a more faithful semantic-level representation of dependency. Furthermore, we design a general framework based on a small pre-trained language model to utilize the dependencies in LLM's reasoning for training and hallucination detection, which can dynamically adjust the pass rate of correct samples through a threshold. Experimental results demonstrate that our method achieves better overall performance compared to state-of-the-art baselines on RAGTruth and Dolly-15k.
Open AccessDetecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph
The Retrieval-augmented generation (RAG) system based on Large language model (LLM) has made significant progress. It can effectively reduce factuality hallucinations, but faithfulness hallucinations still exist. Previous methods for detecting faithfulness hallucinations either neglect to capture the models' internal reasoning processes or handle those features coarsely, making it difficult for discriminators to learn. This paper proposes a semantic-level internal reasoning graph-based method for detecting faithfulness hallucination. Specifically, we first extend the layer-wise relevance propagation algorithm from the token level to the semantic level, constructing an internal reasoning graph based on attribution vectors. This provides a more faithful semantic-level representation of dependency. Furthermore, we design a general framework based on a small pre-trained language model to utilize the dependencies in LLM's reasoning for training and hallucination detection, which can dynamically adjust the pass rate of correct samples through a threshold. Experimental results demonstrate that our method achieves better overall performance compared to state-of-the-art baselines on RAGTruth and Dolly-15k.