Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Liu, Alisa"'
Despite their wide adoption, the biases and unintended behaviors of language models remain poorly understood. In this paper, we identify and characterize a phenomenon never discussed before, which we call semantic leakage, where models leak irrelevan
Externí odkaz:
http://arxiv.org/abs/2408.06518
The pretraining data of today's strongest language models is opaque; in particular, little is known about the proportions of various domains or languages represented. In this work, we tackle a task which we call data mixture inference, which aims to
Externí odkaz:
http://arxiv.org/abs/2407.16607
Autor:
Shi, Ruizhe, Chen, Yifang, Hu, Yushi, Liu, Alisa, Hajishirzi, Hannaneh, Smith, Noah A., Du, Simon
Aligning language models (LMs) to human preferences has emerged as a critical pursuit, enabling these models to better serve diverse user needs. Existing methods primarily focus on optimizing LMs for a single reward function, limiting their adaptabil
Externí odkaz:
http://arxiv.org/abs/2406.18853
Ambiguity is an critical component of language that allows for more effective communication between speakers, but is often ignored in NLP. Recent work suggests that NLP systems may struggle to grasp certain elements of human language understanding be
Externí odkaz:
http://arxiv.org/abs/2403.14072
Despite the general capabilities of large pretrained language models, they consistently benefit from further adaptation to better achieve desired behaviors. However, tuning these models has become increasingly resource-intensive, or impossible when m
Externí odkaz:
http://arxiv.org/abs/2401.08565
The translation of ambiguous text presents a challenge for translation systems, as it requires using the surrounding context to disambiguate the intended meaning as much as possible. While prior work has studied ambiguities that result from different
Externí odkaz:
http://arxiv.org/abs/2310.14610
Autor:
McKenzie, Ian R., Lyzhov, Alexander, Pieler, Michael, Parrish, Alicia, Mueller, Aaron, Prabhu, Ameya, McLean, Euan, Kirtland, Aaron, Ross, Alexis, Liu, Alisa, Gritsevskiy, Andrew, Wurgaft, Daniel, Kauffman, Derik, Recchia, Gabriel, Liu, Jiacheng, Cavanagh, Joe, Weiss, Max, Huang, Sicong, Droid, The Floating, Tseng, Tom, Korbak, Tomasz, Shen, Xudong, Zhang, Yuhui, Zhou, Zhengping, Kim, Najoung, Bowman, Samuel R., Perez, Ethan
Publikováno v:
Transactions on Machine Learning Research (TMLR), 10/2023, https://openreview.net/forum?id=DwgRm72GQF
Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, we present evidence for the claim that LMs may show inverse scaling, or
Externí odkaz:
http://arxiv.org/abs/2306.09479
A major risk of using language models in practical applications is their tendency to hallucinate incorrect statements. Hallucinations are often attributed to knowledge gaps in LMs, but we hypothesize that in some cases, when justifying previously gen
Externí odkaz:
http://arxiv.org/abs/2305.13534
Autor:
Liu, Alisa, Wu, Zhaofeng, Michael, Julian, Suhr, Alane, West, Peter, Koller, Alexander, Swayamdipta, Swabha, Smith, Noah A., Choi, Yejin
Ambiguity is an intrinsic feature of natural language. Managing ambiguity is a key part of human language understanding, allowing us to anticipate misunderstanding as communicators and revise our interpretations as listeners. As language models (LMs)
Externí odkaz:
http://arxiv.org/abs/2304.14399
Autor:
Wang, Yizhong, Kordi, Yeganeh, Mishra, Swaroop, Liu, Alisa, Smith, Noah A., Khashabi, Daniel, Hajishirzi, Hannaneh
Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend heavily on human-written instruction data that is often limi
Externí odkaz:
http://arxiv.org/abs/2212.10560