Výsledky vyhledávání

Report

Improving the Robustness of Large Language Models via Consistency Alignment

Autor: Zhao, Yukun, Yan, Lingyong, Sun, Weiwei, Xing, Guoliang, Wang, Shuaiqiang, Meng, Chong, Cheng, Zhicong, Ren, Zhaochun, Yin, Dawei

Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses due to min

Externí odkaz: http://arxiv.org/abs/2403.14221

Zobrazit plný text záznamu

Report

Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method

Autor: Zhao, Yukun, Yan, Lingyong, Sun, Weiwei, Xing, Guoliang, Meng, Chong, Wang, Shuaiqiang, Cheng, Zhicong, Ren, Zhaochun, Yin, Dawei

Large Language Models (LLMs) have shown great potential in Natural Language Processing (NLP) tasks. However, recent literature reveals that LLMs generate nonfactual responses intermittently, which impedes the LLMs' reliability for further utilization

Externí odkaz: http://arxiv.org/abs/2310.17918

Zobrazit plný text záznamu

Report

DiQAD: A Benchmark Dataset for End-to-End Open-domain Dialogue Assessment

Autor: Zhao, Yukun, Yan, Lingyong, Sun, Weiwei, Meng, Chong, Wang, Shuaiqiang, Cheng, Zhicong, Ren, Zhaochun, Yin, Dawei

Dialogue assessment plays a critical role in the development of open-domain dialogue systems. Existing work are uncapable of providing an end-to-end and human-epistemic assessment dataset, while they only provide sub-metrics like coherence or the dia

Externí odkaz: http://arxiv.org/abs/2310.16319

Zobrazit plný text záznamu