The cooperative formation navigation of multiple unmanned ground vehicles (UGVs) is critical for enhancing the efficiency and safety of intelligent transportation and industrial internet of things systems. However, existing methods remain limited in unknown and complex environments due to insufficient adaptability, a lack of effective path recovery mechanisms, and inflexible formation adjustment, which may lead to motion failure. To address these challenges, this paper proposes an adaptive cooperative formation navigation method based on dynamic tree structure (ACFN-DTree), aiming to achieve feasible path exploration, dynamic decision recovery, and formation self-adaptation. First, a dynamic tree is constructed in obstacle-free regions based on real-time perception, preserving critical environmental information while identifying feasible directions. Then, sub-goals are selected via a spatial cost function and backtracking mechanism, guiding UGVs toward the global goal or returning to feasible branches when deadlocks occur. Furthermore, the formation compression coefficient is optimized based on the effective formation width, allowing for adaptive formation configuration adjustments. Extensive numerical and virtual simulation experiments demonstrate that ACFN-DTree exhibits significant advantages in terms of path length, formation maintenance, and path smoothness level. These results verify the effectiveness of the proposed method in enabling multiple UGVs to achieve safe navigation and adaptive formation adjustment in unknown and complex environments.

Social cognitive theory explains how people learn and acquire knowledge through observing others. Recent years have witnessed the rapid development of large language models (LLMs), which suggests their potential significance as agents in the society. LLMs, as AI agents, can observe external information, which shapes their cognition and behaviors. However, the extent to which external information influences LLMs’ cognition and behaviors remains unclear. This study investigates how external statements and opinions influence LLMs’ thoughts and behaviors from a social cognitive perspective. Three experiments were conducted to explore the effects of external information on LLMs’ memories, opinions, and social media behavioral decisions. Sociocognitive factors, including source authority, social identity, and social role, were analyzed to investigate their moderating effects. Results showed that external information can significantly shape LLMs’ memories, opinions, and behaviors, with these changes mirroring human social cognitive patterns such as authority bias, in-group bias, emotional positivity, and emotion contagion. This underscores the challenges in developing safe and unbiased LLMs, and emphasizes the importance of understanding the susceptibility of LLMs to external influences.

Building machines with commonsense has been a longstanding challenge in NLP due to the reporting bias of commonsense rules and the exposure bias of rule-based commonsense reasoning.In contrast, humans convey and pass down commonsense implicitly through stories.This paper investigates the inherent commonsense ability of large language models (LLMs) expressed through storytelling.We systematically investigate and compare stories and rules for retrieving and leveraging commonsense in LLMs.Experimental results on 28 commonsense QA datasets show that stories outperform rules as the expression for retrieving commonsense from LLMs, exhibiting higher generation confidence and commonsense accuracy.Moreover, stories are the more effective commonsense expression for answering questions regarding daily events, while rules are more effective for scientific questions.This aligns with the reporting bias of commonsense in text corpora.We further show that the correctness and relevance of commonsense stories can be further improved via iterative self-supervised fine-tuning.These findings emphasize the importance of using appropriate language to express, retrieve, and leverage commonsense for LLMs, highlighting a promising direction for better exploiting their commonsense abilities.

Large language models (LLMs) have made significant progress in NLP. However, their ability to memorize, represent, and leverage commonsense knowledge has been a well-known pain point. In this paper, we specifically focus on ChatGPT, a widely used and easily accessible LLM, and ask the following questions: (1) Can ChatGPT effectively answer commonsense questions? (2) Is ChatGPT aware of the underlying commonsense knowledge for answering a specific question? (3) Is ChatGPT knowledgeable in commonsense? (4) Can ChatGPT effectively leverage commonsense for answering questions? We conduct a series of experiments on 11 datasets to evaluate ChatGPT’s commonsense abilities, including answering commonsense questions, identifying necessary knowledge, generating knowledge descriptions, and using knowledge descriptions to answer questions again. Experimental results show that: (1) ChatGPT can achieve good QA accuracies in commonsense tasks, while still struggling with certain domains of datasets. (2) ChatGPT is knowledgeable, and can accurately generate most of the commonsense knowledge using knowledge prompts. (3) Despite its knowledge, ChatGPT is an inexperienced commonsense problem solver, which cannot precisely identify the needed commonsense for answering a specific question. These findings raise the need to explore improved mechanisms for effectively incorporating commonsense into LLMs like ChatGPT, such as better instruction following and commonsense guidance.

A fundamental ability of humans is to utilize commonsense knowledge in language understanding and question answering. In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. However, it remains unclear: (1) How far can we get by exploiting external knowledge for CQA? (2) How much potential of knowledge has been exploited in current CQA models? (3) Which are the most promising directions for future CQA? To answer these questions, we benchmark knowledge-enhanced CQA by conducting extensive experiments on multiple standard CQA datasets using a simple and effective knowledge-to-text transformation framework. Experiments show that: (1) Our knowledge-to-text framework is effective and achieves state-of-the-art performance on CommonsenseQA dataset, providing a simple and strong knowledge-enhanced baseline for CQA; (2) The potential of knowledge is still far from being fully exploited in CQA — there is a significant performance gap from current models to our models with golden knowledge; and (3) Context-sensitive knowledge selection, heterogeneous knowledge exploitation, and commonsense-rich language models are promising CQA directions.