We present a framework - Prompt, Generate, Train (PGT) - to efficiently
develop a generative question-answering model for open-book question-answering
over a proprietary collection of text documents. The framework adapts a
retriever augmented generation model to the target domain using supervised
finetuning and reinforcement learning with synthetic feedback in a few-shot
setting. This yields an aligned, uncertainty calibrated model that is
competitive with GPT-4 based in-context retrieval augmented generation in
generating relevant answers at lower serving costs. The synthetic generation
pipeline generates high quality synthetic training data musing a medium sized
LLM, Flan-T5 XXL, and a novel consistency filtering scheme. The pipeline is
designed to generate both abstractive and extractive questions that span the
entire corpus. Using samples from this dataset, the framework fine-tunes a
smaller RAG model comprising a dense retriever and a smaller sized LLM on
samples from the dataset. In parallel, the framework trains a Reward model to
score domain grounded answers higher than hallucinated answers. In the next
phase, the framework aligns to the RAG model with the target domain using
reinforcement learning. This step improves the RAG model's ability to generate
grounded answers and ignore out of domain questions. In the final phase, the
framework calibrates the model uncertainty for extractive question-answers.
This is a desirable feature since the model can be integrated into a cascading
system where the RAG model's answer is surfaced only when the model is
confident of its answer.

本研究提出了 Prompt，Generate，Train（PGT）框架，用于高效开发基于收集的文本文档的生成式问答模型，并利用监督微调和强化学习方法构建出一个与 GPT-4 类似的生成式 QA 模型。

Prompt Generate Train（PGT）: 一种少样本领域自适应、对齐和不确定性校准框架，用于增强式生成器（RAG）模型在特定领域开放式书籍问答中的应用

Prompt Generate Train (PGT): A framework for few-shot domain adaptation,  alignment, and uncertainty calibration of a retriever augmented generation  (RAG) model for domain specific open book question-answering

Outside-knowledge visual question answering (OK-VQA) requires the agent to
comprehend the image, make use of relevant knowledge from the entire web, and
digest all the information to answer the question. Most previous works address
the problem by first fusing the image and question in the multi-modal space,
which is inflexible for further fusion with a vast amount of external
knowledge. In this paper, we call for a paradigm shift for the OK-VQA task,
which transforms the image into plain text, so that we can enable knowledge
passage retrieval, and generative question-answering in the natural language
space. This paradigm takes advantage of the sheer volume of gigantic knowledge
bases and the richness of pre-trained language models. A
Transform-Retrieve-Generate framework (TRiG) framework is proposed, which can
be plug-and-played with alternative image-to-text models and textual knowledge
bases. Experimental results show that our TRiG framework outperforms all
state-of-the-art supervised methods by at least 11.1% absolute margin.

该论文提出了一种利用海量知识库和预训练语言模型的模型，通过将图像转换为纯文本，以进行知识检索和自然语言生成问答，其中使用的框架为 TRiG 框架，并取得了比所有最先进的监督方法多至少 11.1％的绝对优势。

千言万语胜于一幅图：自然语言为中心的外部知识视觉问答

A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering

Despite the successes of pretrained language models, there are still few
high-quality, general-purpose QA systems that are freely available. In
response, we present Macaw, a versatile, generative question-answering (QA)
system that we are making available to the community. Macaw is built on
UnifiedQA, itself built on T5, and exhibits strong performance, zero-shot, on a
wide variety of topics, including outperforming GPT-3 by over 10% (absolute) on
Challenge300, a suite of 300 challenge questions, despite being an order of
magnitude smaller (11 billion vs. 175 billion parameters). In addition, Macaw
allows different permutations ("angles") of its inputs and outputs to be used,
for example Macaw can take a question and produce an answer; or take an answer
and produce a question; or take an answer and question, and produce
multiple-choice options. We describe the system, and illustrate a variety of
question types where it produces surprisingly good answers, well outside the
training setup. We also identify question classes where it still appears to
struggle, offering insights into the limitations of pretrained language models.
Macaw is freely available, and we hope that it proves useful to the community.
Macaw is available at this https URL

介绍了一种基于预训练语言模型的通用生成式问答系统 ——Macaw，该系统可以灵活处理问题和答案的输入输出，并在大量主题上表现良好，但仍存在一些问题需要解决。

Macaw 实现通用问题解答

General-Purpose Question-Answering with Macaw

Dialog State Tracking (DST), an integral part of modern dialog systems, aims
to track user preferences and constraints (slots) in task-oriented dialogs. In
real-world settings with constantly changing services, DST systems must
generalize to new domains and unseen slot types. Existing methods for DST do
not generalize well to new slot names and many require known ontologies of slot
types and values for inference. We introduce a novel ontology-free framework
that supports natural language queries for unseen constraints and slots in
multi-domain task-oriented dialogs. Our approach is based on generative
question-answering using a conditional language model pre-trained on
substantive English sentences. Our model improves joint goal accuracy in
zero-shot domain adaptation settings by up to 9% (absolute) over the previous
state-of-the-art on the MultiWOZ 2.1 dataset.

研究了一种基于生成型问答和条件语言模型的不需要本体的 Dialog State Tracking 方法，具有较好的领域迁移效果。