Ask Again, Then Fail: Large Language Models' Vacillations in Judgment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909221399822336 |
|---|---|
| author | Xie, Qiming Wang, Zengzhi Feng, Yi Xia, Rui |
| author_facet | Xie, Qiming Wang, Zengzhi Feng, Yi Xia, Rui |
| contents | We observe that current conversational language models often waver in their judgments when faced with follow-up questions, even if the original judgment was correct. This wavering presents a significant challenge for generating reliable responses and building user trust. To comprehensively assess this issue, we introduce a \textsc{Follow-up Questioning Mechanism} along with two metrics to quantify this inconsistency, confirming its widespread presence in current language models. To mitigate this issue, we explore various prompting strategies for closed-source models; moreover, we develop a training-based framework \textsc{Unwavering-FQ} that teaches language models to maintain their originally correct judgments through synthesized high-quality preference data. Our experimental results confirm the effectiveness of our framework and its ability to enhance the general capabilities of models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_02174 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Ask Again, Then Fail: Large Language Models' Vacillations in Judgment Xie, Qiming Wang, Zengzhi Feng, Yi Xia, Rui Computation and Language Artificial Intelligence Machine Learning We observe that current conversational language models often waver in their judgments when faced with follow-up questions, even if the original judgment was correct. This wavering presents a significant challenge for generating reliable responses and building user trust. To comprehensively assess this issue, we introduce a \textsc{Follow-up Questioning Mechanism} along with two metrics to quantify this inconsistency, confirming its widespread presence in current language models. To mitigate this issue, we explore various prompting strategies for closed-source models; moreover, we develop a training-based framework \textsc{Unwavering-FQ} that teaches language models to maintain their originally correct judgments through synthesized high-quality preference data. Our experimental results confirm the effectiveness of our framework and its ability to enhance the general capabilities of models. |
| title | Ask Again, Then Fail: Large Language Models' Vacillations in Judgment |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2310.02174 |