In this paper, we introduce Rule-Guided Feedback (RGF), a framework designed to enhance Large Language Model (LLM) performance through structured rule adherence and strategic information seeking. RGF implements a teacher-student paradigm where rule-following is forced through established guidelines. Our framework employs a Teacher model that rigorously evaluates each student output against task-specific rules, providing constructive guidance rather than direct answers when detecting deviations. This iterative feedback loop serves two crucial purposes: maintaining solutions within defined constraints and encouraging proactive information seeking to resolve uncertainties. We evaluate RGF on diverse tasks including Checkmate-in-One puzzles, Sonnet Writing, Penguins-In-a-Table classification, GSM8k, and StrategyQA. Our findings suggest that structured feedback mechanisms can significantly enhance LLMs' performance across various domains.

An interesting class of commonsense reasoning problems arises when people are faced with natural disasters. To investigate this topic, we present \textsf{RESPONSE}, a human-curated dataset containing 1789 annotated instances featuring 6037 sets of questions designed to assess LLMs' commonsense reasoning in disaster situations across different time frames. The dataset includes problem descriptions, missing resources, time-sensitive solutions, and their justifications, with a subset validated by environmental engineers. Through both automatic metrics and human evaluation, we compare LLM-generated recommendations against human responses. Our findings show that even state-of-the-art models like GPT-4 achieve only 37\% human-evaluated correctness for immediate response actions, highlighting significant room for improvement in LLMs' ability for commonsense reasoning in crises.

While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, understanding and validating their knowledge utilization remains challenging. Chain-of-thought (CoT) prompting partially addresses this by revealing intermediate reasoning steps, but the knowledge flow and application remain implicit. We introduce IAO (Input-Action-Output) prompting, a structured template-based method that explicitly models how LLMs access and apply their knowledge during complex reasoning tasks. IAO decomposes problems into sequential steps, each clearly identifying the input knowledge being used, the action being performed, and the resulting output. This structured decomposition enables us to trace knowledge flow, verify factual consistency, and identify potential knowledge gaps or misapplications. Through experiments across diverse reasoning tasks, we demonstrate that IAO not only improves zero-shot performance but also provides transparency in how LLMs leverage their stored knowledge. Human evaluation confirms that this structured approach enhances our ability to verify knowledge utilization and detect potential hallucinations or reasoning errors. Our findings provide insights into both knowledge representation within LLMs and methods for more reliable knowledge application.

Cooking recipes are one of the most readily available kinds of procedural text. They consist of natural language instructions that can be challenging to interpret. In this paper, we propose a model to identify relevant information from recipes and generate a graph to represent the sequence of actions in the recipe. In contrast with other approaches, we use an unsupervised approach. We iteratively learn the graph structure and the parameters of a $\mathsf{GNN}$ encoding the texts (text-to-graph) one sequence at a time while providing the supervision by decoding the graph into text (graph-to-text) and comparing the generated text to the input. We evaluate the approach by comparing the identified entities with annotated datasets, comparing the difference between the input and output texts, and comparing our generated graphs with those generated by state of the art methods.

Decoding the core of procedural texts, exemplified by cooking recipes, is crucial for intelligent reasoning and instruction automation. Procedural texts can be comprehensively defined as a sequential chain of steps to accomplish a task employing resources. From a cooking perspective, these instructions can be interpreted as a series of modifications to a food preparation, which initially comprises a set of ingredients. These changes involve transformations of comestible resources. For a model to effectively reason about cooking recipes, it must accurately discern and understand the inputs Figure 1: A graphical depiction of the PizzaCommonsense and outputs of intermediate steps within the underlying motivation. Models are required to recipe. Aiming to address this, we present a learn knowledge about the input and output of each intermediate new corpus of cooking recipes enriched with step and predict the correct sequencing of descriptions of intermediate steps of the recipes these comestibles given the corresponding instructions that explicate the input and output for each step.

To used for actions and comestibles; Section 3 presents a address this shortcoming, we propose a high-level representation representation of recipes as bipartite graphs; Section 4 considers of recipes as labelled bipartite graphs where the acceptability of recipes; Section 5 presents definitions first subset of nodes denotes the comestibles involved in the for comparing recipes; Section 6 presents definitions for recipe (ingredients, intermediate food items, final products, composition of recipes from subrecipes; Section 7 presents i.e. dishes, and by-products) and the second subset of nodes substitution based on changing the type of nodes; Section 8 denotes actions on those comestibles. The edges reflect the presents substitution based on changing the structure of the (possibly partial) sequence of steps taken in the recipe going graph; Section 9 discusses related literature; and Section 10 from the ingredients to final products.

The human ability to repurpose objects and processes is universal, but it is not a well-understood aspect of human intelligence. Repurposing arises in everyday situations such as finding substitutes for missing ingredients when cooking, or for unavailable tools when doing DIY. It also arises in critical, unprecedented situations needing crisis management. After natural disasters and during wartime, people must repurpose the materials and processes available to make shelter, distribute food, etc. Repurposing is equally important in professional life (e.g. clinicians often repurpose medicines off-license) and in addressing societal challenges (e.g. finding new roles for waste products,). Despite the importance of repurposing, the topic has received little academic attention. By considering examples from a variety of domains such as every-day activities, drug repurposing and natural disasters, we identify some principle characteristics of the process and describe some technical challenges that would be involved in modelling and simulating it. We consider cases of both substitution, i.e. finding an alternative for a missing resource, and exploitation, i.e. identifying a new role for an existing resource. We argue that these ideas could be developed into general formal theory of repurposing, and that this could then lead to the development of AI methods based on commonsense reasoning, argumentation, ontological reasoning, and various machine learning methods, to develop tools to support repurposing in practice.

We show that compact fully connected (FC) deep learning networks trained to classify wireless protocols using a hierarchy of multiple denoising autoencoders (AEs) outperform reference FC networks trained in a typical way, i.e., with a stochastic gradient based optimization of a given FC architecture. Not only is the complexity of such FC network, measured in number of trainable parameters and scalar multiplications, much lower than the reference FC and residual models, its accuracy also outperforms both models for nearly all tested SNR values (0 dB to 50dB). Such AE-trained networks are suited for in-situ protocol inference performed by simple mobile devices based on noisy signal measurements. Training is based on the data transmitted by real devices, and collected in a controlled environment, and systematically augmented by a policy-based data synthesis process by adding to the signal any subset of impairments commonly seen in a wireless receiver.

While research on adversarial examples in machine learning for images has been prolific, similar attacks on deep learning (DL) for radio frequency (RF) signals and their mitigation strategies are scarcely addressed in the published work, with only one recent publication in the RF domain [1]. RF adversarial examples (AdExs) can cause drastic, targeted misclassification results mostly in spectrum sensing/ survey applications (e.g. BPSK mistaken for 8-PSK) with minimal waveform perturbation. It is not clear if the RF AdExs maintain their effects in the physical world, i.e., when AdExs are delivered over-the-air (OTA). Our research on deep learning AdExs and proposed defense mechanisms are RF-centric, and incorporate physical world, OTA effects. We here present defense mechanisms based on statistical tests. One test to detect AdExs utilizes Peak-to- Average-Power-Ratio (PAPR) of the DL data points delivered OTA, while another statistical test uses the Softmax outputs of the DL classifier, which corresponds to the probabilities the classifier assigns to each of the trained classes. The former test leverages the RF nature of the data, and the latter is universally applicable to AdExs regardless of their origin. Both solutions are shown as viable mitigation methods to subvert adversarial attacks against communications and radar sensing systems.

Adversarial examples in machine learning for images are widely publicized and explored. Illustrations of misclassifications caused by slightly perturbed inputs are abundant and commonly known (e.g., a picture of panda imperceptibly perturbed to fool the classifier into incorrectly labeling it as a gibbon). Similar attacks on deep learning (DL) for radio frequency (RF) signals and their mitigation strategies are scarcely addressed in the published work. Yet, RF adversarial examples (AdExs) with minimal waveform perturbations can cause drastic, targeted misclassification results, particularly against spectrum sensing/survey applications (e.g. BPSK is mistaken for 8-PSK). Our research on deep learning AdExs and proposed defense mechanisms are RF-centric, and incorporate physical world, over-the-air (OTA) effects. We herein present defense mechanisms based on pre-training the target classifier using an autoencoder. Our results validate this approach as a viable mitigation method to subvert adversarial attacks against deep learning-based communications and radar sensing systems.