Zobrazeno 1 - 10
of 944
pro vyhledávání: '"Lewis, Patrick A."'
Autor:
Verga, Pat, Hofstatter, Sebastian, Althammer, Sophia, Su, Yixuan, Piktus, Aleksandra, Arkhangorodsky, Arkady, Xu, Minjie, White, Naomi, Lewis, Patrick
As Large Language Models (LLMs) have become more advanced, they have outpaced our abilities to accurately evaluate their quality. Not only is finding data to adequately probe particular model properties difficult, but evaluating the correctness of a
Externí odkaz:
http://arxiv.org/abs/2404.18796
Autor:
Li, Yuhong, Huang, Yingbing, Yang, Bowen, Venkitesh, Bharat, Locatelli, Acyr, Ye, Hanchen, Cai, Tianle, Lewis, Patrick, Chen, Deming
Large Language Models (LLMs) have made remarkable progress in processing extensive contexts, with the Key-Value (KV) cache playing a vital role in enhancing their performance. However, the growth of the KV cache in response to increasing input length
Externí odkaz:
http://arxiv.org/abs/2404.14469
To date, toxicity mitigation in language models has almost entirely been focused on single-language settings. As language models embrace multilingual capabilities, it's crucial our safety measures keep pace. Recognizing this research gap, our approac
Externí odkaz:
http://arxiv.org/abs/2403.03893
Dense retrievers compress source documents into (possibly lossy) vector representations, yet there is little analysis of what information is lost versus preserved, and how it affects downstream tasks. We conduct the first analysis of the information
Externí odkaz:
http://arxiv.org/abs/2402.15925
Listwise rerankers based on large language models (LLM) are the zero-shot state-of-the-art. However, current works in this direction all depend on the GPT models, making it a single point of failure in scientific reproducibility. Moreover, it raises
Externí odkaz:
http://arxiv.org/abs/2312.02969
Considerable effort has been dedicated to mitigating toxicity, but existing methods often require drastic modifications to model parameters or the use of computationally intensive auxiliary models. Furthermore, previous approaches have often neglecte
Externí odkaz:
http://arxiv.org/abs/2310.07589
Perception of toxicity evolves over time and often differs between geographies and cultural backgrounds. Similarly, black-box commercially available APIs for detecting toxicity, such as the Perspective API, are not static, but frequently retrained to
Externí odkaz:
http://arxiv.org/abs/2304.12397
Prior work shows that it is possible to expand pretrained Masked Language Models (MLMs) to new languages by learning a new set of embeddings, while keeping the transformer body frozen. Despite learning a small subset of parameters, this approach is n
Externí odkaz:
http://arxiv.org/abs/2212.10503