Webgpt: Browser-assisted question-answering with human feedback

R Nakano, J Hilton, S Balaji, J Wu, L Ouyang… - arxiv preprint arxiv …, 2021 - arxiv.org
We fine-tune GPT-3 to answer long-form questions using a text-based web-browsing
environment, which allows the model to search and navigate the web. By setting up the task …

Generate rather than retrieve: Large language models are strong context generators

W Yu, D Iter, S Wang, Y Xu, M Ju, S Sanyal… - arxiv preprint arxiv …, 2022 - arxiv.org
Knowledge-intensive tasks, such as open-domain question answering (QA), require access
to a large amount of world or domain knowledge. A common approach for knowledge …

Teaching language models to support answers with verified quotes

J Menick, M Trebacz, V Mikulik, J Aslanides… - arxiv preprint arxiv …, 2022 - arxiv.org
Recent large language models often answer factual questions correctly. But users can't trust
any given claim a model makes without fact-checking, because language models can …

A survey of text classification with transformers: How wide? how large? how long? how accurate? how expensive? how safe?

J Fields, K Chovanec, P Madiraju - IEEE Access, 2024 - ieeexplore.ieee.org
Text classification in natural language processing (NLP) is evolving rapidly, particularly with
the surge in transformer-based models, including large language models (LLM). This paper …

Longrag: Enhancing retrieval-augmented generation with long-context llms

Z Jiang, X Ma, W Chen - arxiv preprint arxiv:2406.15319, 2024 - arxiv.org
In traditional RAG framework, the basic retrieval units are normally short. The common
retrievers like DPR normally work with 100-word Wikipedia paragraphs. Such a design …

Kg-fid: Infusing knowledge graph in fusion-in-decoder for open-domain question answering

D Yu, C Zhu, Y Fang, W Yu, S Wang, Y Xu… - arxiv preprint arxiv …, 2021 - arxiv.org
Current Open-Domain Question Answering (ODQA) model paradigm often contains a
retrieving module and a reading module. Given an input question, the reading module …

Chain-of-note: Enhancing robustness in retrieval-augmented language models

W Yu, H Zhang, X Pan, K Ma, H Wang, D Yu - arxiv preprint arxiv …, 2023 - arxiv.org
Retrieval-augmented language models (RALMs) represent a substantial advancement in
the capabilities of large language models, notably in reducing factual hallucination by …

A survey of knowledge-intensive nlp with pre-trained language models

D Yin, L Dong, H Cheng, X Liu, KW Chang… - arxiv preprint arxiv …, 2022 - arxiv.org
With the increasing of model capacity brought by pre-trained language models, there
emerges boosting needs for more knowledgeable natural language processing (NLP) …

[KSIĄŻKA][B] Neural approaches to conversational information retrieval

J Gao, C **ong, P Bennett, N Craswell - 2023 - Springer
A conversational information retrieval (CIR) system is an information retrieval (IR) system
with a conversational interface, which allows users to interact with the system to seek …

Neurips 2020 efficientqa competition: Systems, analyses and lessons learned

S Min, J Boyd-Graber, C Alberti… - NeurIPS 2020 …, 2021 - proceedings.mlr.press
We review the EfficientQA competition from NeurIPS 2020. The competition focused on open-
domain question answering (QA), where systems take natural language questions as input …