Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Malon, Christopher"'
Autor:
Malon, Christopher
Separating disinformation from fact on the web has long challenged both the search and the reasoning powers of humans. We show that the reasoning power of large language models (LLMs) and the retrieval power of modern search engines can be combined t
Externí odkaz:
http://arxiv.org/abs/2411.05762
When performing complex multi-step reasoning tasks, the ability of Large Language Models (LLMs) to derive structured intermediate proof steps is important for ensuring that the models truly perform the desired reasoning and for improving models' expl
Externí odkaz:
http://arxiv.org/abs/2410.08436
Autor:
Malon, Christopher, Zhu, Xiaodan
Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this work, we exte
Externí odkaz:
http://arxiv.org/abs/2403.00696
Autor:
Malon, Christopher
When faced with a large number of product reviews, it is not clear that a human can remember all of them and weight opinions representatively to write a good reference summary. We propose an automatic metric to test the prevalence of the opinions tha
Externí odkaz:
http://arxiv.org/abs/2307.14305
Autor:
Widjaja, Haris, Gashteovski, Kiril, Rim, Wiem Ben, Liu, Pengfei, Malon, Christopher, Ruffinelli, Daniel, Lawrence, Carolin, Neubig, Graham
Knowledge Graphs (KGs) store information in the form of (head, predicate, tail)-triples. To augment KGs with new knowledge, researchers proposed models for KG Completion (KGC) tasks such as link prediction; i.e., answering (h; p; ?) or (?; p; t) quer
Externí odkaz:
http://arxiv.org/abs/2208.11024
We study few-shot debugging of transformer based natural language understanding models, using recently popularized test suites to not just diagnose but correct a problem. Given a few debugging examples of a certain phenomenon, and a held-out test set
Externí odkaz:
http://arxiv.org/abs/2204.06555
Autor:
Malon, Christopher
Modern natural language understanding models depend on pretrained subword embeddings, but applications may need to reason about words that were never or rarely seen during pretraining. We show that examples that depend critically on a rarer word are
Externí odkaz:
http://arxiv.org/abs/2103.03842
Robustness against adversarial attack in neural networks is an important research topic in the machine learning community. We observe one major source of vulnerability of neural nets is from overparameterized fully-connected layers. In this paper, we
Externí odkaz:
http://arxiv.org/abs/2101.11766
Autor:
Cheng, Pengyu, Min, Martin Renqiang, Shen, Dinghan, Malon, Christopher, Zhang, Yizhe, Li, Yitong, Carin, Lawrence
Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms of data,
Externí odkaz:
http://arxiv.org/abs/2006.00693
Autor:
Malon, Christopher, Bai, Bing
We propose a framework for answering open domain multi-hop questions in which partial information is read and used to generate followup questions, to finally be answered by a pretrained single-hop answer extractor. This framework makes each hop inter
Externí odkaz:
http://arxiv.org/abs/2002.12344