Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Ram, Ori"'
Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance when it is re
Externí odkaz:
http://arxiv.org/abs/2310.01558
Autor:
Muhlgay, Dor, Ram, Ori, Magar, Inbal, Levine, Yoav, Ratner, Nir, Belinkov, Yonatan, Abend, Omri, Leyton-Brown, Kevin, Shashua, Amnon, Shoham, Yoav
Before deploying a language model (LM) within a given domain, it is important to measure its tendency to generate factually incorrect information in that domain. Existing methods for factuality evaluation of LLM generation focus on facts sampled from
Externí odkaz:
http://arxiv.org/abs/2307.06908
Autor:
Ram, Ori, Levine, Yoav, Dalmedigos, Itay, Muhlgay, Dor, Shashua, Amnon, Leyton-Brown, Kevin, Shoham, Yoav
Retrieval-Augmented Language Modeling (RALM) methods, which condition a language model (LM) on relevant documents from a grounding corpus during generation, were shown to significantly improve language modeling performance. In addition, they can miti
Externí odkaz:
http://arxiv.org/abs/2302.00083
Autor:
Ratner, Nir, Levine, Yoav, Belinkov, Yonatan, Ram, Ori, Magar, Inbal, Abend, Omri, Karpas, Ehud, Shashua, Amnon, Leyton-Brown, Kevin, Shoham, Yoav
When applied to processing long text, Large Language Models (LLMs) are limited by their context window. Existing efforts to address this limitation involve training specialized architectures, and cannot be easily applied to off-the-shelf LLMs. We pre
Externí odkaz:
http://arxiv.org/abs/2212.10947
Dual encoders are now the dominant architecture for dense retrieval. Yet, we have little understanding of how they represent text, and why this leads to good performance. In this work, we shed light on this question via distributions over the vocabul
Externí odkaz:
http://arxiv.org/abs/2212.10380
Autor:
Levine, Yoav, Dalmedigos, Itay, Ram, Ori, Zeldes, Yoel, Jannai, Daniel, Muhlgay, Dor, Osin, Yoni, Lieber, Opher, Lenz, Barak, Shalev-Shwartz, Shai, Shashua, Amnon, Leyton-Brown, Kevin, Shoham, Yoav
Huge pretrained language models (LMs) have demonstrated surprisingly good zero-shot capabilities on a wide variety of tasks. This gives rise to the appealing vision of a single, versatile model with a wide range of functionalities across disparate ap
Externí odkaz:
http://arxiv.org/abs/2204.10019
Causal transformer language models (LMs), such as GPT-3, typically require some form of positional encoding, such as positional embeddings. However, we show that LMs without any explicit positional encoding are still competitive with standard models,
Externí odkaz:
http://arxiv.org/abs/2203.16634
Dense retrievers for open-domain question answering (ODQA) have been shown to achieve impressive performance by training on large datasets of question-passage pairs. In this work we ask whether this dependence on labeled data can be reduced via unsup
Externí odkaz:
http://arxiv.org/abs/2112.07708
Fine-tuned language models use greedy decoding to answer reading comprehension questions with relative success. However, this approach does not ensure that the answer is a span in the given passage, nor does it guarantee that it is the most probable
Externí odkaz:
http://arxiv.org/abs/2108.05857
In several question answering benchmarks, pretrained models have reached human parity through fine-tuning on an order of 100,000 annotated questions and answers. We explore the more realistic few-shot setting, where only a few hundred training exampl
Externí odkaz:
http://arxiv.org/abs/2101.00438