Zobrazeno 1 - 10
of 261
pro vyhledávání: '"Zemel, Richard"'
When presented with questions involving visual thinking, humans naturally switch reasoning modalities, often forming mental images or drawing visual aids. Large language models have shown promising results in arithmetic and symbolic reasoning by expr
Externí odkaz:
http://arxiv.org/abs/2406.14562
We formulate a unifying framework for unsupervised continual learning (UCL), which disentangles learning objectives that are specific to the present and the past data, encompassing stability, plasticity, and cross-task consolidation. The framework re
Externí odkaz:
http://arxiv.org/abs/2404.19132
Recent advancement in large language models (LLMs) has offered a strong potential for natural language systems to process informal language. A representative form of informal language is slang, used commonly in daily conversations and online social m
Externí odkaz:
http://arxiv.org/abs/2404.02323
Autor:
Feng, Tiantian, Ramakrishna, Anil, Majmudar, Jimit, Peris, Charith, Wang, Jixuan, Chung, Clement, Zemel, Richard, Ziyadi, Morteza, Gupta, Rahul
Federated Learning (FL) is a popular algorithm to train machine learning models on user data constrained to edge devices (for example, mobile phones) due to privacy concerns. Typically, FL is trained with the assumption that no part of the user data
Externí odkaz:
http://arxiv.org/abs/2403.01615
Autor:
Creager, Elliot, Zemel, Richard
Research on algorithmic recourse typically considers how an individual can reasonably change an unfavorable automated decision when interacting with a fixed decision-making system. This paper focuses instead on the online setting, where system parame
Externí odkaz:
http://arxiv.org/abs/2401.00055
Designing deep neural network classifiers that perform robustly on distributions differing from the available training data is an active area of machine learning research. However, out-of-distribution generalization for regression-the analogous probl
Externí odkaz:
http://arxiv.org/abs/2312.17463
Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
Autor:
Ovalle, Anaelia, Mehrabi, Ninareh, Goyal, Palash, Dhamala, Jwala, Chang, Kai-Wei, Zemel, Richard, Galstyan, Aram, Pinter, Yuval, Gupta, Rahul
Gender-inclusive NLP research has documented the harmful limitations of gender binary-centric large language models (LLM), such as the inability to correctly use gender-diverse English neopronouns (e.g., xe, zir, fae). While data scarcity is a known
Externí odkaz:
http://arxiv.org/abs/2312.11779
Large pretrained language models (LLMs) can be rapidly adapted to a wide variety of tasks via a text-to-text approach, where the instruction and input are fed to the model in natural language. Combined with in-context learning (ICL), this paradigm is
Externí odkaz:
http://arxiv.org/abs/2312.07405
Autor:
Zollo, Thomas P., Morrill, Todd, Deng, Zhun, Snell, Jake C., Pitassi, Toniann, Zemel, Richard
The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task. While it may be tempting to simply choose a prompt based on average performance on a validation set
Externí odkaz:
http://arxiv.org/abs/2311.13628
Autor:
Mehrabi, Ninareh, Goyal, Palash, Ramakrishna, Anil, Dhamala, Jwala, Ghosh, Shalini, Zemel, Richard, Chang, Kai-Wei, Galstyan, Aram, Gupta, Rahul
With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance. Here we introduce a joint framework in which we simultaneously probe and improve the robustness
Externí odkaz:
http://arxiv.org/abs/2311.09473