← Search

Zexin Jian

2 accepted papers

2024

Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering

NeurIPS 2024poster

Large Language Models (LLMs) are widely used for knowledge-seeking purposes yet suffer from hallucinations. The knowledge boundary of an LLM limits its factual understanding, beyond which it may begin to hallucinate. Investigating the perception of LLMs' knowledge boundary is crucial for detecting h…

Cited by 4SourcePDFScholar
2023

GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation

ACL 2023findings

Attribute-based generation methods are of growing significance in controlling the generation of large pre-trained language models (PLMs). Existing studies control the generation by (1) finetuning the model with attributes or (2) guiding the inference processing toward control signals while freezing…