Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Reif, Emily"'
Autor:
Ghandeharioun, Asma, Yuan, Ann, Guerard, Marius, Reif, Emily, Lepori, Michael A., Dixon, Lucas
Despite investments in improving model safety, studies show that misaligned capabilities remain latent in safety-tuned models. In this work, we shed light on the mechanics of this phenomenon. First, we show that even when model generations are safe,
Externí odkaz:
http://arxiv.org/abs/2406.12094
As large language models (LLMs) become more advanced and impactful, it is increasingly important to scrutinize the data that they rely upon and produce. What is it to be a dataset practitioner doing this work? We approach this in two parts: first, we
Externí odkaz:
http://arxiv.org/abs/2402.16611
Making sense of unstructured text datasets is perennially difficult, yet increasingly relevant with Large Language Models. Data workers often rely on dataset summaries, especially distributions of various derived features. Some features, like toxicit
Externí odkaz:
http://arxiv.org/abs/2402.14880
Autor:
Kahng, Minsuk, Tenney, Ian, Pushkarna, Mahima, Liu, Michael Xieyang, Wexler, James, Reif, Emily, Kallarackal, Krystal, Chang, Minsuk, Terry, Michael, Dixon, Lucas
Automatic side-by-side evaluation has emerged as a promising approach to evaluating the quality of responses from large language models (LLMs). However, analyzing the results from this evaluation approach raises scalability and interpretability chall
Externí odkaz:
http://arxiv.org/abs/2402.10524
The unstructured nature of data used in foundation model development is a challenge to systematic analyses for making data use and documentation decisions. From a Responsible AI perspective, these decisions often rely upon understanding how people ar
Externí odkaz:
http://arxiv.org/abs/2311.17259
Publikováno v:
Published in EMNLP 2023
Large language models achieve high performance on many but not all downstream tasks. The interaction between pretraining data and task data is commonly assumed to determine this variance: a task with data that is more similar to a model's pretraining
Externí odkaz:
http://arxiv.org/abs/2311.09006
Autor:
Longpre, Shayne, Yauney, Gregory, Reif, Emily, Lee, Katherine, Roberts, Adam, Zoph, Barret, Zhou, Denny, Wei, Jason, Robinson, Kevin, Mimno, David, Ippolito, Daphne
Pretraining is the preliminary and fundamental step in developing capable language models (LM). Despite this, pretraining data design is critically under-documented and often guided by empirically unsupported intuitions. To address this, we pretrain
Externí odkaz:
http://arxiv.org/abs/2305.13169
Large language models (LLMs) can be used to generate smaller, more refined datasets via few-shot prompting for benchmarking, fine-tuning or other use cases. However, understanding and evaluating these datasets is difficult, and the failure modes of L
Externí odkaz:
http://arxiv.org/abs/2305.11364
Autor:
Anil, Rohan, Dai, Andrew M., Firat, Orhan, Johnson, Melvin, Lepikhin, Dmitry, Passos, Alexandre, Shakeri, Siamak, Taropa, Emanuel, Bailey, Paige, Chen, Zhifeng, Chu, Eric, Clark, Jonathan H., Shafey, Laurent El, Huang, Yanping, Meier-Hellstern, Kathy, Mishra, Gaurav, Moreira, Erica, Omernick, Mark, Robinson, Kevin, Ruder, Sebastian, Tay, Yi, Xiao, Kefan, Xu, Yuanzhong, Zhang, Yujing, Abrego, Gustavo Hernandez, Ahn, Junwhan, Austin, Jacob, Barham, Paul, Botha, Jan, Bradbury, James, Brahma, Siddhartha, Brooks, Kevin, Catasta, Michele, Cheng, Yong, Cherry, Colin, Choquette-Choo, Christopher A., Chowdhery, Aakanksha, Crepy, Clément, Dave, Shachi, Dehghani, Mostafa, Dev, Sunipa, Devlin, Jacob, Díaz, Mark, Du, Nan, Dyer, Ethan, Feinberg, Vlad, Feng, Fangxiaoyu, Fienber, Vlad, Freitag, Markus, Garcia, Xavier, Gehrmann, Sebastian, Gonzalez, Lucas, Gur-Ari, Guy, Hand, Steven, Hashemi, Hadi, Hou, Le, Howland, Joshua, Hu, Andrea, Hui, Jeffrey, Hurwitz, Jeremy, Isard, Michael, Ittycheriah, Abe, Jagielski, Matthew, Jia, Wenhao, Kenealy, Kathleen, Krikun, Maxim, Kudugunta, Sneha, Lan, Chang, Lee, Katherine, Lee, Benjamin, Li, Eric, Li, Music, Li, Wei, Li, YaGuang, Li, Jian, Lim, Hyeontaek, Lin, Hanzhao, Liu, Zhongtao, Liu, Frederick, Maggioni, Marcello, Mahendru, Aroma, Maynez, Joshua, Misra, Vedant, Moussalem, Maysam, Nado, Zachary, Nham, John, Ni, Eric, Nystrom, Andrew, Parrish, Alicia, Pellat, Marie, Polacek, Martin, Polozov, Alex, Pope, Reiner, Qiao, Siyuan, Reif, Emily, Richter, Bryan, Riley, Parker, Ros, Alex Castro, Roy, Aurko, Saeta, Brennan, Samuel, Rajkumar, Shelby, Renee, Slone, Ambrose, Smilkov, Daniel, So, David R., Sohn, Daniel, Tokumine, Simon, Valter, Dasha, Vasudevan, Vijay, Vodrahalli, Kiran, Wang, Xuezhi, Wang, Pidong, Wang, Zirui, Wang, Tao, Wieting, John, Wu, Yuhuai, Xu, Kelvin, Xu, Yunhan, Xue, Linting, Yin, Pengcheng, Yu, Jiahui, Zhang, Qiao, Zheng, Steven, Zheng, Ce, Zhou, Weikang, Zhou, Denny, Petrov, Slav, Wu, Yonghui
We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 is a Transformer-based model trained using a mixture of objectives. Thr
Externí odkaz:
http://arxiv.org/abs/2305.10403
Publikováno v:
NAACL 2022 Findings
The task of inserting text into a specified position in a passage, known as fill in the blank (FitB), is useful for a variety of applications where writers interact with a natural language generation (NLG) system to craft text. While previous work ha
Externí odkaz:
http://arxiv.org/abs/2206.04812