Procedural planning, which entails decomposing a high-level goal into a
sequence of temporally ordered steps, is an important yet intricate task for
machines. It involves integrating common-sense knowledge to reason about
complex contextualized situations that are often counterfactual, e.g.
"scheduling a doctor's appointment without a phone". While current approaches
show encouraging results using large language models (LLMs), they are hindered
by drawbacks such as costly API calls and reproducibility issues. In this
paper, we advocate planning using smaller language models. We present PlaSma, a
novel two-pronged approach to endow small language models with procedural
knowledge and (counterfactual) planning capabilities. More concretely, we
develop symbolic procedural knowledge distillation to enhance the implicit
knowledge in small language models and an inference-time algorithm to
facilitate more structured and accurate reasoning. In addition, we introduce a
novel task, Counterfactual Planning, that requires a revision of a plan to cope
with a counterfactual situation. In both the original and counterfactual
setting, we show that orders-of-magnitude smaller models (770M-11B parameters)
can compete and often surpass their larger teacher models' capabilities.

本文提出了 PlaSma，一种利用小型语言模型赋予程序化知识和（反事实的）规划能力的新方法，并介绍了计划的符号化程序知识蒸馏和推理时间算法以及一个新的任务，即对计划进行修订以应对反事实情况的 “反事实规划”，并展示了在原始和反事实情况下，规模比大的教师模型（770M-11B 参数）小几个数量级的模型可以达到甚至超越它们的能力。

PlaSma: 将小型语言模型转化为更好的规程知识模型，用于（反事实的）规划

PlaSma: Making Small Language Models Better Procedural Knowledge Models  for (Counterfactual) Planning

Online resources such as WikiHow compile a wide range of scripts for
performing everyday tasks, which can assist models in learning to reason about
procedures. However, the scripts are always presented in a linear manner, which
does not reflect the flexibility displayed by people executing tasks in real
life. For example, in the CrossTask Dataset, 64.5% of consecutive step pairs
are also observed in the reverse order, suggesting their ordering is not fixed.
In addition, each step has an average of 2.56 frequent next steps,
demonstrating "branching". In this paper, we propose the new challenging task
of non-sequential graph script induction, aiming to capture optional and
interchangeable steps in procedural planning. To automate the induction of such
graph scripts for given tasks, we propose to take advantage of loosely aligned
videos of people performing the tasks. In particular, we design a multimodal
framework to ground procedural videos to WikiHow textual steps and thus
transform each video into an observed step path on the latent ground truth
graph script. This key transformation enables us to train a script knowledge
model capable of both generating explicit graph scripts for learnt tasks and
predicting future steps given a partial step sequence. Our best model
outperforms the strongest pure text/vision baselines by 17.52% absolute gains
on F1@3 for next step prediction and 13.8% absolute gains on Acc@1 for partial
sequence completion. Human evaluation shows our model outperforming the WikiHow
linear baseline by 48.76% absolute gains in capturing sequential and
non-sequential step relationships.

该论文提出了一种新的具有挑战性的任务，即非顺序图脚本推理，旨在捕捉程序规划中的可选步骤和可互换步骤，通过多模态框架将视频转换成观察到的步骤路径，以训练生成明确图脚本和预测未来步骤的模型。该模型优于纯文本 / 视觉基线，人类评估显示超过 WikiHow 线性基线，能够更好地捕捉顺序和非顺序步骤关系。

通过多媒体基础实现非顺序图脚本归纳

Non-Sequential Graph Script Induction via Multimedia Grounding

Procedural planning aims to implement complex high-level goals by
decomposition into sequential simpler low-level steps. Although procedural
planning is a basic skill set for humans in daily life, it remains a challenge
for large language models (LLMs) that lack a deep understanding of the
cause-effect relations in procedures. Previous methods require manual exemplars
to acquire procedural planning knowledge from LLMs in the zero-shot setting.
However, such elicited pre-trained knowledge in LLMs induces spurious
correlations between goals and steps, which impair the model generalization to
unseen tasks. In contrast, this paper proposes a neuro-symbolic procedural
PLANner (PLAN) that elicits procedural planning knowledge from the LLMs with
commonsense-infused prompting. To mitigate spurious goal-step correlations, we
use symbolic program executors on the latent procedural representations to
formalize prompts from commonsense knowledge bases as a causal intervention
toward the Structural Causal Model. Both automatic and human evaluations on
WikiHow and RobotHow show the superiority of PLAN on procedural planning
without further training or manual exemplars.

本文提出了一个名为 PLAN 的神经符号化程序规划器，通过依赖于常识信仰，从大型语言模型中获取程序式计划知识，并使用符号程序执行器对潜在程序式表示进行形式化的干预， 最终在非零样本的 WikiHow 和 RobotHow 数据集上展现出 PLAN 在程序规划方面的卓越表现。