Zobrazeno 1 - 10
of 2 276
pro vyhledávání: '"P Borenstein"'
Much theoretical work has described the ability of transformers to represent formal languages. However, linking theoretical results to empirical performance is not straightforward due to the complex interplay between the architecture, the learning al
Externí odkaz:
http://arxiv.org/abs/2410.03001
Autor:
Wright, Dustin, Arora, Arnav, Borenstein, Nadav, Yadav, Srishti, Belongie, Serge, Augenstein, Isabelle
Uncovering latent values and opinions embedded in large language models (LLMs) can help identify biases and mitigate potential harm. Recently, this has been approached by prompting LLMs with survey questions and quantifying the stances in the outputs
Externí odkaz:
http://arxiv.org/abs/2406.19238
Autor:
Borenstein, Nadav, Svete, Anej, Chan, Robin, Valvoda, Josef, Nowak, Franz, Augenstein, Isabelle, Chodroff, Eleanor, Cotterell, Ryan
What can large language models learn? By definition, language models (LM) are distributions over strings. Therefore, an intuitive way of addressing the above question is to formalize it as a matter of learnability of classes of distributions over str
Externí odkaz:
http://arxiv.org/abs/2406.04289
Studying human values is instrumental for cross-cultural research, enabling a better understanding of preferences and behaviour of society at large and communities therein. To study the dynamics of communities online, we propose a method to computati
Externí odkaz:
http://arxiv.org/abs/2402.14177
Autor:
Emuna, Hen, Borenstein, Nadav, Qian, Xin, Kang, Hyeonsu, Chan, Joel, Kittur, Aniket, Shahaf, Dafna
Biologically Inspired Design (BID), or Biomimicry, is a problem-solving methodology that applies analogies from nature to solve engineering challenges. For example, Speedo engineers designed swimsuits based on shark skin. Finding relevant biological
Externí odkaz:
http://arxiv.org/abs/2312.12681
Autor:
Wang, Yuxia, Reddy, Revanth Gangi, Mujahid, Zain Muhammad, Arora, Arnav, Rubashevskii, Aleksandr, Geng, Jiahui, Afzal, Osama Mohammed, Pan, Liangming, Borenstein, Nadav, Pillai, Aditya, Augenstein, Isabelle, Gurevych, Iryna, Nakov, Preslav
The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs. In this work, we present a holistic end-to-end solution for annotating the factuality
Externí odkaz:
http://arxiv.org/abs/2311.09000
The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlo
Externí odkaz:
http://arxiv.org/abs/2310.18343
We conducted ethnographic research with 31 misinformation creators and consumers in Brazil and the US before, during, and after a major election to understand the consumption and production of election and medical misinformation. This study contribut
Externí odkaz:
http://arxiv.org/abs/2308.02377
Autor:
Borenstein, Nadav, Stańczak, Karolina, Rolskov, Thea, Perez, Natália da Silva, Käfer, Natacha Klein, Augenstein, Isabelle
Data-driven analyses of biases in historical texts can help illuminate the origin and development of biases prevailing in modern society. However, digitised historical documents pose a challenge for NLP practitioners as these corpora suffer from erro
Externí odkaz:
http://arxiv.org/abs/2305.12376
NLP methods can aid historians in analyzing textual materials in greater volumes than manually feasible. Developing such methods poses substantial challenges though. First, acquiring large, annotated historical datasets is difficult, as only domain e
Externí odkaz:
http://arxiv.org/abs/2305.10928