arXiv subjects

Francisco Ribeiro

Publications and source records attributed to Francisco Ribeiro.

5 recordsLinked to original sources

arXiv2026

On the Robustness of LLMs' Internal Representation of Code Correctness

Code generated by modern language models often reads naturally. Yet, it also often fails to implement what was asked. This should be no surprise, as research shows the models' own confidence signals are poorly calibrated with actual correctness. A promising way to assess correctness looks inside the model: by contrasting the hidden states of correct and incorrect programs, recent work captured an internal signal of code correctness that is able to judge candidate solutions better than the model's token-level or stated confidence, with no test execution. However, this signal was captured under one particular way, leaving open an important question: whether it reflects a robust property of the model or an artifact of that choice. We study this question systematically, varying how the signal is extracted from the model internals. Besides this, we also ask if the signal's quality is limited by the data used to extract it, by constructing program pairs that differ only in the fault that makes them incorrect. Our results show that no single configuration is best, and that isolating the fault does not help.

cs.SE↗

arXiv2026

A Vision-based Framework for Intelligent gNodeB Mobility Control

This paper proposes a vision-based framework for the intelligent control of mobile Open Radio Access Network (O-RAN) base stations (gNBs) operating in dynamic wireless environments. The framework comprises three innovative components. The first is the introduction of novel Service Models (SMs) within a vision-enabled O-RAN architecture, termed VisionRAN. These SMs extend state-of-the-art O-RAN-based architectures by enabling the transmission of vision-based sensing data and gNB positioning control messages. The second is an O-RAN xApp, VisionApp, which fuses vision and radio data, and uses this information to control the position of a mobile gNB, using a Deep Q-Network (DQN). The third is a digital twin environment, VisionTwin, which incorporates vision data and can emulate realistic wireless scenarios; this digital twin was used to train the DQN running in VisionApp and validate the overall system. Experimental results, obtained using real vision data and an emulated radio, demonstrate that the proposed approach reduces the duration of Line-of-Sight (LoS) blockages by up to 75% compared to a static gNB. These findings confirm the viability of integrating multimodal perception and learning-based control within RANs.

cs.NI↗

arXiv2026

On LLMs' Internal Representation of Code Correctness

Despite the effectiveness of large language models (LLMs) for code generation, they often output incorrect code. One reason is that model output probabilities are often not well-correlated with correctness, and reflect only the final output of the generation process. Inspired by findings that LLMs internally encode concepts like truthfulness, this paper explores if LLMs similarly represent code correctness. Specifically, we identify a correctness representation inside LLMs by contrasting the hidden states between pairs of correct and incorrect code for the same programming tasks. By experimenting on four LLMs, we show that exploiting this extracted correctness representation outperforms standard log-likelihood ranking, as well as verbalized model confidence. Furthermore, we explore how this internal correctness signal can be used to select higher-quality code samples, without requiring test execution. Ultimately, this work demonstrates how leveraging internal representations can enhance code generation systems and make LLMs more reliable, thus improving confidence in automatically generated code.

cs.SE↗

arXiv2025

Detecting and Fixing API Misuses of Data Science Libraries Using Large Language Models

Data science libraries, such as scikit-learn and pandas, specialize in processing and manipulating data. The data-centric nature of these libraries makes the detection of API misuse in them more challenging. This paper introduces DSCHECKER, an LLM-based approach designed for detecting and fixing API misuses of data science libraries. We identify two key pieces of information, API directives and data information, that may be beneficial for API misuse detection and fixing. Using three LLMs and misuses from five data science libraries, we experiment with various prompts. We find that incorporating API directives and data-specific details enhances Dschecker's ability to detect and fix API misuses, with the best-performing model achieving a detection F1-score of 61.18 percent and fixing 51.28 percent of the misuses. Building on these results, we implement Dschecker agent which includes an adaptive function calling mechanism to access information on demand, simulating a real-world setting where information about the misuse is unknown in advance. We find that Dschecker agent achieves 48.65 percent detection F1-score and fixes 39.47 percent of the misuses, demonstrating the promise of LLM-based API misuse detection and fixing in real-world scenarios.

cs.SE↗

arXiv2025

Human Activity Recognition with a 6.5 GHz Reconfigurable Intelligent Surface for Wi-Fi 6E

Human Activity Recognition (HAR) is the identification and classification of static and dynamic human activities, which find applicability in domains like healthcare, entertainment, security, and cyber-physical systems. Traditional HAR approaches rely on wearable sensors, vision-based systems, or ambient sensing, each with inherent limitations such as privacy concerns or restricted sensing conditions. Recently, Radio Frequency (RF)-based HAR has emerged, relying on the interaction of RF signals with people to infer activities. Reconfigurable Intelligent Surfaces (RISs) offers significant potential in this domain by enabling dynamic control over the wireless environment, thus enhancing the information extracted from RF signals. We present an Hand Gesture Recognition (HGR) approach that employs our own 6.5 GHz RIS design to manipulate the RF medium in an area of interest. We validate the capability of our RIS to control the medium by characterizing its steering response, and further we gather and publish a dataset for HGR classification for three different hand gestures. By employing two Convolutional Neural Networks (CNNs) models trained on data gathered under random and optimized RIS configuration sequences, we achieved classification accuracies exceeding 90%.

eess.SP↗