Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Yehudai, Asaf"'
Autor:
Gupta, Sonam, Nandwani, Yatin, Yehudai, Asaf, Mishra, Mayank, Pandey, Gaurav, Raghu, Dinesh, Joshi, Sachindra
Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task or the ch
Externí odkaz:
http://arxiv.org/abs/2409.04787
Autor:
Perlitz, Yotam, Gera, Ariel, Arviv, Ofir, Yehudai, Asaf, Bandel, Elron, Shnarch, Eyal, Shmueli-Scheuer, Michal, Choshen, Leshem
Recent advancements in Language Models (LMs) have catalyzed the creation of multiple benchmarks, designed to assess these models' general capabilities. A crucial task, however, is assessing the validity of the benchmarks themselves. This is most comm
Externí odkaz:
http://arxiv.org/abs/2407.13696
Most works on gender bias focus on intrinsic bias -- removing traces of information about a protected group from the model's internal representation. However, these works are often disconnected from the impact of such debiasing on downstream applicat
Externí odkaz:
http://arxiv.org/abs/2406.00787
Cross-domain alignment refers to the task of mapping a concept from one domain to another. For example, ``If a \textit{doctor} were a \textit{color}, what color would it be?''. This seemingly peculiar task is designed to investigate how people repres
Externí odkaz:
http://arxiv.org/abs/2405.14863
Autor:
Yehudai, Asaf, Bendel, Elron
We present FastFit, a method, and a Python package design to provide fast and accurate few-shot classification, especially for scenarios with many semantically similar classes. FastFit utilizes a novel approach integrating batch contrastive learning
Externí odkaz:
http://arxiv.org/abs/2404.12365
Autor:
Yehudai, Asaf, Carmeli, Boaz, Mass, Yosi, Arviv, Ofir, Mills, Nathaniel, Toledo, Assaf, Shnarch, Eyal, Choshen, Leshem
The lack of high-quality data for content-grounded generation tasks has been identified as a major obstacle to advancing these tasks. To address this gap, we propose Genie, a novel method for automatically generating high-quality content-grounded dat
Externí odkaz:
http://arxiv.org/abs/2401.14367
Intent detection with semantically similar fine-grained intents is a challenging task. To address it, we reformulate intent detection as a question-answering retrieval task by treating utterances and intent names as questions and answers. To that end
Externí odkaz:
http://arxiv.org/abs/2303.01593
Machine translation (MT) requires a wide range of linguistic capabilities, which current end-to-end models are expected to learn implicitly by observing aligned sentences in bilingual corpora. In this work, we ask: \emph{How well do MT models learn c
Externí odkaz:
http://arxiv.org/abs/2302.08464
Applying Reinforcement learning (RL) following maximum likelihood estimation (MLE) pre-training is a versatile method for enhancing neural machine translation (NMT) performance. However, recent work has argued that the gains produced by RL for NMT ar
Externí odkaz:
http://arxiv.org/abs/2210.03053
We deal with the scenario of conversational search, where user queries are under-specified or ambiguous. This calls for a mixed-initiative setup. User-asks (queries) and system-answers, as well as system-asks (clarification questions) and user respon
Externí odkaz:
http://arxiv.org/abs/2112.07308