Search Results for author:
Found 7 papers, 7 papers with code
Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation
This paper studies retrieval-augmented approaches for personalizing large language models (LLMs), which potentially have a substantial impact on various applications and domains.
Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering
The proposed approach leads to 26. 9% Precision@5 improvements compared to the current state-of-the-art asymmetric architecture.
A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering
Utilizing the passages retrieved by DEDR, we further introduce MM-FiD, an encoder-decoder multi-modal fusion-in-decoder model, for generating a textual answer for KI-VQA tasks.
LaMP: When Large Language Models Meet Personalization
This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing personalized outputs.
PEACH: Pre-Training Sequence-to-Sequence Multilingual Models for Translation with Semi-Supervised Pseudo-Parallel Document Generation
Multilingual pre-training on monolingual data ignores the availability of parallel data in many language pairs.
ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization
Current pre-training works in abstractive summarization give more points to the summaries with more words in common with the main text and pay less attention to the semantic similarity between generated sentences and the original document.
UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models
Detecting which parts of a sentence contribute to that sentence's toxicity -- rather than providing a sentence-level verdict of hatefulness -- would increase the interpretability of models and allow human moderators to better understand the outputs of the system.
