Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Baumler, Connor"'
Autor:
Baumler, Connor, Daumé III, Hal
AI-based systems such as language models can replicate and amplify social biases reflected in their training data. Among other questionable behavior, this can lead to LM-generated text--and text suggestions--that contain normatively inappropriate ste
Externí odkaz:
http://arxiv.org/abs/2409.20390
AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against some protecte
Externí odkaz:
http://arxiv.org/abs/2310.08617
Autor:
Goyal, Navita, Briakou, Eleftheria, Liu, Amanda, Baumler, Connor, Bonial, Claire, Micher, Jeffrey, Voss, Clare R., Carpuat, Marine, Daumé III, Hal
NLP systems have shown impressive performance at answering questions by retrieving relevant context. However, with the increasingly large models, it is impossible and often undesirable to constrain models' knowledge or reasoning to only the retrieved
Externí odkaz:
http://arxiv.org/abs/2305.14331
Autor:
Baumler, Connor
In this thesis, we consider the problem of generating natural language given a communicative goal and a world description. The meaning representation of sentences, world and goal have a significant impact on the generative process. Different meaning
Autor:
Goyal, Navita, Briakou, Eleftheria, Liu, Amanda, Baumler, Connor, Bonial, Claire, Micher, Jeffrey, Voss, Clare R., Carpuat, Marine, Daumé, Hal
AI systems have shown impressive performance at answering questions by retrieving relevant context. However, with the increasingly large models, it is impossible and often undesirable to constrain models' knowledge or reasoning to only the retrieved
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::296775db23bc5890bfe3f20063edef40
http://arxiv.org/abs/2305.14331
http://arxiv.org/abs/2305.14331