Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913512152891392 |
|---|---|
| author | Zhao, Jinman Zhang, Xueyan Yue, Xingyu Chen, Weizhe Qian, Zifan Wang, Ruiyu |
| author_facet | Zhao, Jinman Zhang, Xueyan Yue, Xingyu Chen, Weizhe Qian, Zifan Wang, Ruiyu |
| contents | Current common interactions with language models is through full inference. This approach may not necessarily align with the model's internal knowledge. Studies show discrepancies between prompts and internal representations. Most focus on sentence understanding. We study the discrepancy of word semantics understanding in internal and external mismatch across Encoder-only, Decoder-only, and Encoder-Decoder pre-trained language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13972 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch Zhao, Jinman Zhang, Xueyan Yue, Xingyu Chen, Weizhe Qian, Zifan Wang, Ruiyu Computation and Language Current common interactions with language models is through full inference. This approach may not necessarily align with the model's internal knowledge. Studies show discrepancies between prompts and internal representations. Most focus on sentence understanding. We study the discrepancy of word semantics understanding in internal and external mismatch across Encoder-only, Decoder-only, and Encoder-Decoder pre-trained language models. |
| title | Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.13972 |