Large Language Models (LLMs) have achieved remarkable performance in
objective tasks such as open-domain question answering and mathematical
reasoning, which can often be solved through recalling learned factual
knowledge or chain-of-thought style reasoning. However, we find that the
performance of LLMs in subjective tasks is still unsatisfactory, such as
metaphor recognition, dark humor detection, etc. Compared to objective tasks,
subjective tasks focus more on interpretation or emotional response rather than
a universally accepted reasoning pathway. Based on the characteristics of the
tasks and the strong dialogue-generation capabilities of LLMs, we propose RiC
(Reasoning in Conversation), a method that focuses on solving subjective tasks
through dialogue simulation. The motivation of RiC is to mine useful contextual
information by simulating dialogues instead of supplying chain-of-thought style
rationales, thereby offering potential useful knowledge behind dialogues for
giving the final answers. We evaluate both API-based and open-source LLMs
including GPT-4, ChatGPT, and OpenChat across twelve tasks. Experimental
results show that RiC can yield significant improvement compared with various
baselines.

通过对话模拟，我们提出了 RiC (Reasoning in Conversation) 方法，用于解决主观任务，并提供了实验证明 RiC 可以显著改善大型语言模型在此类任务中的表现。

对话中的推理：通过大型语言模型的模拟解决主观任务

Reasoning in Conversation: Solving Subjective Tasks through Dialogue  Simulation for Large Language Models

Building dialogue systems requires a large corpus of annotated dialogues.
Such datasets are usually created via crowdsourcing, which is expensive and
time-consuming. In this paper, we propose \textsc{Dialogic}, a novel dialogue
simulation method based on large language model in-context learning to automate
dataset creation. Seeded with a few annotated dialogues, \textsc{Dialogic}
automatically selects in-context examples for demonstration and prompts GPT-3
to generate new dialogues and annotations in a controllable way. Our method can
rapidly expand a small set of dialogue data with minimum or zero \textit{human
involvement} and \textit{parameter update} and is thus much more cost-efficient
and time-saving than crowdsourcing. Experimental results on the MultiWOZ
dataset demonstrate that training a model on the simulated dialogues leads to
even better performance than using the same amount of human-generated dialogues
under the challenging low-resource settings, with as few as 85 dialogues as a
seed. When enough data is available, our method can still serve as an effective
data augmentation method. Human evaluation results also show that our simulated
dialogues have near-human fluency and annotation accuracy. The code and data
are available at \textbf{https://github.com/Leezekun/dialogic}.

这篇论文介绍了一种使用大型语言模型进行对话模拟的方法 ——	extsc {Dialogic}，它能够自动选择示例并在 GPT-3 的帮助下生成新的对话和注释，快速扩展小型对话数据集，从而实现更高效和省时的数据集创建。同时，该方法可作为一种有效的数据增强方法，具有接近人类流畅性和注释准确性的模拟对话可以代替人工标注的数据进行模型训练。

对话式：具有上下文学习的可控对话模拟

Dialogic: Controllable Dialogue Simulation with In-Context Learning

Existing studies on semantic parsing focus primarily on mapping a
natural-language utterance to a corresponding logical form in one turn.
However, because natural language can contain a great deal of ambiguity and
variability, this is a difficult challenge. In this work, we investigate an
interactive semantic parsing framework that explains the predicted logical form
step by step in natural language and enables the user to make corrections
through natural-language feedback for individual steps. We focus on question
answering over knowledge bases (KBQA) as an instantiation of our framework,
aiming to increase the transparency of the parsing process and help the user
appropriately trust the final answer. To do so, we construct INSPIRED, a
crowdsourced dialogue dataset derived from the ComplexWebQuestions dataset. Our
experiments show that the interactive framework with human feedback has the
potential to greatly improve overall parse accuracy. Furthermore, we develop a
pipeline for dialogue simulation to evaluate our framework w.r.t. a variety of
state-of-the-art KBQA models without involving further crowdsourcing effort.
The results demonstrate that our interactive semantic parsing framework
promises to be effective across such models.

本研究研究了一种交互式语义解析框架，它可以通过自然语言一步一步地解释预测的逻辑形式，并允许用户通过自然语言反馈进行更正，主要关注问答和知识库的关系，构建了 INSPIRED 数据集，并进行了实验，有望大大提高总体解析精度。