Robustness of LLMs
 |
 |
@courseproject{merolajaspinderothmane2425-ethicsofai20242025,
abstract = {Large language models (LLMs) have demonstrated impressive emergent abilities across diverse natural language tasks, yet their capacity for structured planning remains under-explored. This project investigates whether the LLaMA model can reliably solve planning problems and introduces a meta-network to evaluate and manage its performance. First, we construct a benchmark suite of planning prompts and record LLaMA’s responses. Next, we train a lightweight meta-network atop these examples to predict, for each prompt, (a) the likelihood that LLaMA’s answer is correct, and (b) a confidence score. When the meta-network predicts low confidence or high error risk, the system automatically delegates the task to alternative solvers or human experts. Our framework provides a generalizable mechanism for risk-aware deployment of LLMs balancing autonomy with reliable fallback strategies.},
apice = {MerolaJaspinderOthmane2425},
author = {Carlo Merola and Jaspinder Singh and Othmane Dardouri},
howpublished = {Ethics of AI, A.Y. 2024/2025},
sort = {classic},
supervisor = {Calegari, Roberta},
title = {Robustness of LLMs},
type = {Standard Project},
url = {https://dvcs.apice.unibo.it/pika-lab/courses/ai-ethics/projects/merolasinghdardouri2425}
}
abstract = {Large language models (LLMs) have demonstrated impressive emergent abilities across diverse natural language tasks, yet their capacity for structured planning remains under-explored. This project investigates whether the LLaMA model can reliably solve planning problems and introduces a meta-network to evaluate and manage its performance. First, we construct a benchmark suite of planning prompts and record LLaMA’s responses. Next, we train a lightweight meta-network atop these examples to predict, for each prompt, (a) the likelihood that LLaMA’s answer is correct, and (b) a confidence score. When the meta-network predicts low confidence or high error risk, the system automatically delegates the task to alternative solvers or human experts. Our framework provides a generalizable mechanism for risk-aware deployment of LLMs balancing autonomy with reliable fallback strategies.},
apice = {MerolaJaspinderOthmane2425},
author = {Carlo Merola and Jaspinder Singh and Othmane Dardouri},
howpublished = {Ethics of AI, A.Y. 2024/2025},
sort = {classic},
supervisor = {Calegari, Roberta},
title = {Robustness of LLMs},
type = {Standard Project},
url = {https://dvcs.apice.unibo.it/pika-lab/courses/ai-ethics/projects/merolasinghdardouri2425}
}