Gotcha! Don't trick me with unanswerable questions! Self-aligning Large Language Models for...

[PDF] arxiv.org

H2RSVLM: Towards Helpful and Honest Remote Sensing Large Vision Language Model

C Pang, J Wu, J Li, Y Liu, J Sun, W Li, X Weng… - arXiv preprint arXiv …, 2024 - arxiv.org
The generic large Vision-Language Models (VLMs) is rapidly developing, but still perform
poorly in Remote Sensing (RS) domain, which is due to the unique and specialized nature …
被引用次数：8 相关文章 所有 2 个版本
[PDF] arxiv.org

Right this way: Can VLMs Guide Us to See More to Answer Questions?

L Liu, D Yang, S Zhong, KSS Tholeti, L Ding… - arXiv preprint arXiv …, 2024 - arxiv.org
In question-answering scenarios, humans can assess whether the available information is
sufficient and seek additional information if necessary, rather than providing a forced …
相关文章 所有 2 个版本
[PDF] arxiv.org

When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems

A Saadat, TB Sogir, MTA Chowdhury, S Aziz - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) are increasingly relied upon to solve complex mathematical
word problems. However, being susceptible to hallucination, they may generate inaccurate …
相关文章 所有 2 个版本
[PDF] arxiv.org

Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing

W Liu, S An, J Lu, M Wu, T Li, X Wang, X Zheng… - arXiv preprint arXiv …, 2024 - arxiv.org
Role-Playing Agents (RPAs) have shown remarkable performance in various applications,
yet they often struggle to recognize and appropriately respond to hard queries that conflict …
相关文章 所有 2 个版本