Author name cluster

Cristina Cornelio

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

ICML Conference 2025 Conference Paper

Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification

Flavio Petruzzellis
Cristina Cornelio
Pietro Liò

Large Language Models (LLMs) have shown promise as robotic planners but often struggle with long-horizon and complex tasks, especially in specialized environments requiring external knowledge. While hierarchical planning and Retrieval-Augmented Generation (RAG) address some of these challenges, they remain insufficient on their own and a deeper integration is required for achieving more reliable systems. To this end, we propose a neuro-symbolic approach that enhances LLMs-based planners with Knowledge Graph-based RAG for hierarchical plan generation. This method decomposes complex tasks into manageable subtasks, further expanded into executable atomic action sequences. To ensure formal correctness and proper decomposition, we integrate a Symbolic Validator, which also functions as a failure detector by aligning expected and observed world states. Our evaluation against baseline methods demonstrates the consistent significant advantages of integrating hierarchical planning, symbolic verification, and RAG across tasks of varying complexity and different LLMs. Additionally, our experimental setup and novel metrics not only validate our approach for complex planning but also serve as a tool for assessing LLMs’ reasoning and compositional capabilities. Code available at https: //github. com/corneliocristina/HVR.

Details

IROS Conference 2024 Conference Paper

Recover: A Neuro-Symbolic Framework for Failure Detection and Recovery

Cristina Cornelio
Mohammed Diab

Recognizing failures during task execution and implementing recovery procedures is challenging in robotics. Traditional approaches rely on the availability of extensive data or a tight set of constraints, while more recent approaches leverage large language models (LLMs) to verify task steps and replan accordingly. However, these methods often operate offline, necessitating scene resets and incurring in high costs. This paper introduces Recover, a neuro-symbolic framework for online failure identification and recovery. By integrating ontologies, logical rules, and LLM-based planners, Recover exploits symbolic information to enhance the ability of LLMs to generate recovery plans and also to decrease the associated costs. In order to demonstrate the capabilities of our method in a simulated kitchen environment, we introduce OntoThor, an ontology describing the AI2Thor simulator setting. Empirical evaluation shows that OntoThor’s logical rules accurately detect all failures in the analyzed tasks, and that Recover considerably outperforms, for both failure detection and recovery, a baseline method reliant solely on LLMs. Supplementary material, including the OntoThor ontology, is available at: https://recover-ontothor.github.io.

Details

NeSy Conference 2023 Conference Paper

Learning Where and When to Reason in Neuro-Symbolic Inference

Cristina Cornelio
Jan Stühmer
Shell Xu Hu
Timothy M. Hospedales

The imposition of hard constraints on the output of neural networks is a highly desirable capability, as it instills confidence in AI by ensuring that neural network predictions adhere to domain expertise. This area has received significant attention recently, however, current methods typically enforce constraints in a ”weak” form during training, with no guarantees at inference, and do not provide a general framework for different tasks/constraint types. We approach this open problem from a neuro-symbolic perspective. Our method enhances a conventional neural predictor with a reasoning module that can correct predictions errors and a neural attention module that learns to focus the reasoning effort on potential prediction errors while leaving other outputs unchanged. This framework provides a balance between the efficiency of unconstrained neural inference and the high cost of exhaustive reasoning during inference.

Details

ICLR Conference 2023 Conference Paper

Learning where and when to reason in neuro-symbolic inference

Cristina Cornelio
Jan Stühmer
Shell Xu Hu
Timothy M. Hospedales

The integration of hard constraints on neural network outputs is a very desirable capability. This allows to instill trust in AI by guaranteeing the sanity of that neural network predictions with respect to domain knowledge. Recently, this topic has received a lot of attention. However, all the existing methods usually either impose the constraints in a "weak" form at training time, with no guarantees at inference, or fail to provide a general framework that supports different tasks and constraint types. We tackle this open problem from a neuro-symbolic perspective. Our pipeline enhances a conventional neural predictor with (1) a symbolic reasoning module capable of correcting structured prediction errors and (2) a neural attention module that learns to direct the reasoning effort to focus on potential prediction errors, while keeping other outputs unchanged. This framework provides an appealing trade-off between the efficiency of constraint-free neural inference and the prohibitive cost of exhaustive reasoning at inference time. We show that our method outperforms the state of the art on visual-Sudoku, and can also benefit visual scene graph prediction. Furthermore, it can improve the performance of existing neuro-symbolic systems that lack our explicit reasoning during inference.

Details

AAMAS Conference 2022 Conference Paper

Voting with Random Classifiers (VORACE): Theoretical and Experimental Analysis

Cristina Cornelio
Michele Donini
Andrea Loreggia
Maria Silvia Pini
Francesca Rossi

Ensemble methods are built by training many different models and aggregating their outputs to output the prediction of the whole system. In this work, we study the behavior of an ensemble method where voting rules are used to aggregate the output of a set of randomly-generated classifiers. We provide both a theoretical and an empirical analysis of this method, showing that it performs comparably with other state-of-the-art ensemble methods, while not requiring any domain expertise to fine-tune the individual classifiers.

PDF

AAAI Conference 2021 Conference Paper

A Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving

Maxwell Crouse
Ibrahim Abdelaziz
Bassem Makni
Spencer Whitehead
Cristina Cornelio
Pavan Kapanipathi
Kavitha Srinivas
Veronika Thost

Automated theorem provers have traditionally relied on manually tuned heuristics to guide how they perform proof search. Deep reinforcement learning has been proposed as a way to obviate the need for such heuristics, however, its deployment in automated theorem proving remains a challenge. In this paper we introduce TRAIL, a system that applies deep reinforcement learning to saturation-based theorem proving. TRAIL leverages (a) a novel neural representation of the state of a theorem prover and (b) a novel characterization of the inference selection process in terms of an attention-based action policy. We show through systematic analysis that these mechanisms allow TRAIL to significantly outperform previous reinforcementlearning-based theorem provers on two benchmark datasets for first-order logic automated theorem proving (proving around 15% more theorems).

PDF Details

JAIR Journal 2021 Journal Article

Reasoning with PCP-Nets

Cristina Cornelio
Judy Goldsmith
Umberto Grandi
Nicholas Mattei
Francesca Rossi
K. Brent Venable

We introduce PCP-nets, a formalism to model qualitative conditional preferences with probabilistic uncertainty. PCP-nets generalise CP-nets by allowing for uncertainty over the preference orderings. We define and study both optimality and dominance queries in PCP-nets, and we propose a tractable approximation of dominance which we show to be very accurate in our experimental setting. Since PCP-nets can be seen as a way to model a collection of weighted CP-nets, we also explore the use of PCP-nets in a multi-agent context, where individual agents submit CP-nets which are then aggregated into a single PCP-net. We consider various ways to perform such aggregation and we compare them via two notions of scores, based on well known voting theory concepts. Experimental results allow us to identify the aggregation method that better represents the given set of CP-nets and the most efficient dominance procedure to be used in the multi-agent context.

PDF Details DOI

JAAMAS Journal 2021 Journal Article

Voting with random classifiers (VORACE): theoretical and experimental analysis

Cristina Cornelio
Michele Donini
Francesca Rossi

Abstract In many machine learning scenarios, looking for the best classifier that fits a particular dataset can be very costly in terms of time and resources. Moreover, it can require deep knowledge of the specific domain. We propose a new technique which does not require profound expertise in the domain and avoids the commonly used strategy of hyper-parameter tuning and model selection. Our method is an innovative ensemble technique that uses voting rules over a set of randomly-generated classifiers. Given a new input sample, we interpret the output of each classifier as a ranking over the set of possible classes. We then aggregate these output rankings using a voting rule, which treats them as preferences over the classes. We show that our approach obtains good results compared to the state-of-the-art, both providing a theoretical analysis and an empirical evaluation of the approach on several datasets.

Details DOI

JAAMAS Journal 2019 Journal Article

Multi-agent soft constraint aggregation via sequential voting: theoretical and experimental results

Cristina Cornelio
Maria Silvia Pini
Kristen Brent Venable

Abstract We consider scenarios where several agents must aggregate their preferences over a large set of candidates with a combinatorial structure. That is, each candidate is an element of the Cartesian product of the domains of some variables (i. e. , features). These scenarios are very common when candidates are described by feature vectors, such as cars, or houses, or any complex product. We assume agents to compactly express their preferences over the candidates via soft constraints. This is a compact way to model preferences which naturally models variables domains, and relationship among variables. To aggregate the preferences of the agents, we consider a sequential procedure that asks the agents to vote on one variable at a time. At each step, all agents express their preferences over the domain of a variable; based on such preferences, a voting rule is used to select one value for that variable. When all variables have been considered, the selected values constitute the returned variable assignment, that is, the elected candidate. We study several properties of this procedure (such as Condorcet consistency, anonymity, neutrality, monotonicity, consistency, efficiency, participation, independence of irrelevant alternatives, non dictatorship, and strategy-proofness), by relating them to corresponding properties of the adopted voting rules used for each variable. Moreover, we perform an experimental study on a special kind of soft constraints, namely fuzzy constraints. The experimental study shows that the proposed sequential procedure yields a considerable saving in time with respect to a non-sequential approach, while the winners satisfy the agents just as well, independently of the variable ordering, and of the presence of coalitions of agents.

Details DOI

IJCAI Conference 2015 Conference Paper

Models for Conditional Preferences as extensions of CP-nets

Cristina Cornelio

This paper presents two frameworks that generalize Conditional Preference networks (CP-nets). The first generalization is the LCP-theory, first order logic theory that provides a rich framework to express preferences. The the second generalization, the PCP-networks, is a probabilistic generalization of CP-nets that models conditional preferences with uncertainty.

PDF Details