← Search

Zhaoxin Feng

2 accepted papers

2025

Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention

ACL 2025long

Autoregressive Large Language Models (LLMs) demonstrate exceptional performance in language understanding and generation. However, their application in text embedding tasks has been relatively slow, along with the analysis of their semantic representation in probing tasks, due to the constraints of…

Cited by 0SourcePDFScholar
2025

PhonoThink: Improving Large Language Models’ Reasoning on Chinese Phonological Ambiguities

EMNLP 2025

Effectively resolving phonological ambiguities is crucial for robust natural language processing, as these ambiguities are pervasive in tasks ranging from speech-to-text, spelling correction, to offensive language detection. However, current Large Language Models (LLMs) frequently struggle to resolv

Cited by 0SourcePDFScholar