Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Adolphs, Leonard"'
Standard language model training employs gold human documents or human-human interaction data, and treats all training data as positive examples. Growing evidence shows that even with very large amounts of positive training data, issues remain that c
Externí odkaz:
http://arxiv.org/abs/2211.05826
Autor:
Adolphs, Leonard, Huebscher, Michelle Chen, Buck, Christian, Girgin, Sertan, Bachem, Olivier, Ciaramita, Massimiliano, Hofmann, Thomas
Neural retrieval models have superseded classic bag-of-words methods such as BM25 as the retrieval framework of choice. However, neural systems lack the interpretability of bag-of-words models; it is not trivial to connect a query change to a change
Externí odkaz:
http://arxiv.org/abs/2210.12084
Autor:
Shuster, Kurt, Komeili, Mojtaba, Adolphs, Leonard, Roller, Stephen, Szlam, Arthur, Weston, Jason
Language models (LMs) have recently been shown to generate more factual responses by employing modularity (Zhou et al., 2021) in combination with retrieval (Adolphs et al., 2021). We extend the recent approach of Adolphs et al. (2021) to include inte
Externí odkaz:
http://arxiv.org/abs/2203.13224
In typical machine learning systems, an estimate of the probability of the prediction is used to assess the system's confidence in the prediction. This confidence measure is usually uncalibrated; i.e.\ the system's confidence in the prediction does n
Externí odkaz:
http://arxiv.org/abs/2203.10623
Large language models can produce fluent dialogue but often hallucinate factual inaccuracies. While retrieval-augmented models help alleviate this issue, they still face a difficult challenge of both reasoning to provide correct knowledge and generat
Externí odkaz:
http://arxiv.org/abs/2111.05204
Autor:
Adolphs, Leonard, Boerschinger, Benjamin, Buck, Christian, Huebscher, Michelle Chen, Ciaramita, Massimiliano, Espeholt, Lasse, Hofmann, Thomas, Kilcher, Yannic, Rothe, Sascha, Sessa, Pier Giuseppe, Saralegui, Lierni Sestorain
This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. Our approach uses machine reading to guide the selection of refinement terms from aggregated
Externí odkaz:
http://arxiv.org/abs/2109.00527
Large pre-trained language models (LMs) are capable of not only recovering linguistic but also factual and commonsense knowledge. To access the knowledge stored in mask-based LMs, we can use cloze-style questions and let the model fill in the blank.
Externí odkaz:
http://arxiv.org/abs/2108.01928
Autor:
Adolphs, Leonard, Hofmann, Thomas
While Reinforcement Learning (RL) approaches lead to significant achievements in a variety of areas in recent history, natural language tasks remained mostly unaffected, due to the compositional and combinatorial nature that makes them notoriously ha
Externí odkaz:
http://arxiv.org/abs/1909.01646
We investigate the use of regularized Newton methods with adaptive norms for optimizing neural networks. This approach can be seen as a second-order counterpart of adaptive gradient methods, which we here show to be interpretable as first-order trust
Externí odkaz:
http://arxiv.org/abs/1905.09201
Gradient-based optimization methods are the most popular choice for finding local optima for classical minimization and saddle point problems. Here, we highlight a systemic issue of gradient dynamics that arise for saddle point problems, namely the p
Externí odkaz:
http://arxiv.org/abs/1805.05751