Large Language Models (LLMs) are increasingly used for boosting
organizational efficiency and automating tasks. While not originally designed
for complex cognitive processes, recent efforts have further extended to employ
LLMs in activities such as reasoning, planning, and decision-making. In
business processes, such abilities could be invaluable for leveraging on the
massive corpora LLMs have been trained on for gaining deep understanding of
such processes. In this work, we plant the seeds for the development of a
benchmark to assess the ability of LLMs to reason about causal and process
perspectives of business operations. We refer to this view as
Causally-augmented Business Processes (BP^C). The core of the benchmark
comprises a set of BP^C related situations, a set of questions about these
situations, and a set of deductive rules employed to systematically resolve the
ground truth answers to these questions. Also with the power of LLMs, the seed
is then instantiated into a larger-scale set of domain-specific situations and
questions. Reasoning on BP^C is of crucial importance for process interventions
and process improvement. Our benchmark could be used in one of two possible
modalities: testing the performance of any target LLM and training an LLM to
advance its capability to reason about BP^C.

利用大型语言模型 (LLMs) 来推动组织效率和自动化任务，在本研究中创建了一个基准来评估 LLMs 在推理业务活动的因果和过程视角方面的能力，并应用 LLMs 的能力进行 BP^C 的推理，以用于流程干预和流程改进。

面向使用 LLMs 的因果业务流程推理的基准

Towards a Benchmark for Causal Business Process Reasoning with LLMs

Increasing the success rate of a process, i.e. the percentage of cases that
end in a positive outcome, is a recurrent process improvement goal. At runtime,
there are often certain actions (a.k.a. treatments) that workers may execute to
lift the probability that a case ends in a positive outcome. For example, in a
loan origination process, a possible treatment is to issue multiple loan offers
to increase the probability that the customer takes a loan. Each treatment has
a cost. Thus, when defining policies for prescribing treatments to cases,
managers need to consider the net gain of the treatments. Also, the effect of a
treatment varies over time: treating a case earlier may be more effective than
later in a case. This paper presents a prescriptive monitoring method that
automates this decision-making task. The method combines causal inference and
reinforcement learning to learn treatment policies that maximize the net gain.
The method leverages a conformal prediction technique to speed up the
convergence of the reinforcement learning mechanism by separating cases that
are likely to end up in a positive or negative outcome, from uncertain cases.
An evaluation on two real-life datasets shows that the proposed method
outperforms a state-of-the-art baseline.

该论文提出了一种监控方法来自动化制定决策规则，此方法应用因果推断和强化学习结合来实现增加处理成功率的目标。

学习何时处理业务流程：带因果推理和强化学习的处方式流程监控

Learning When to Treat Business Processes: Prescriptive Process Monitoring with Causal Inference and Reinforcement Learning

Process mining is a set of techniques that are used by organizations to
understand and improve their operational processes. The first essential step in
designing any process reengineering procedure is to find process improvement
opportunities. In existing work, it is usually assumed that the set of
problematic process instances in which an undesirable outcome occurs is known
prior or is easily detectable. So the process enhancement procedure involves
finding the root causes and the treatments for the problem in those process
instances. For example, the set of problematic instances is considered as those
with outlier values or with values smaller/bigger than a given threshold in one
of the process features. However, on various occasions, using this approach,
many process enhancement opportunities, not captured by these problematic
process instances, are missed. To overcome this issue, we formulate finding the
process enhancement areas as a context-sensitive anomaly/outlier detection
problem. We define a process enhancement area as a set of situations (process
instances or prefixes of process instances) where the process performance is
surprising. We aim to characterize those situations where process
performance/outcome is significantly different from what was expected
considering its performance/outcome in similar situations. To evaluate the
validity and relevance of the proposed approach, we have implemented and
evaluated it on several real-life event logs.

本研究提出了一种基于上下文的异常检测方法，用于识别未被传统流程改善方法所捕捉的流程增强机会，通过分析事件日志中的流程实例或前缀，发现性能意外显着不同于类似情况下的流程性能。