Manuel Borroto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Manuel Borroto has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Francesco Ricca
University of Calabria
8 shared publications - Alessandra Russo
Imperial College London
3 shared publications - Antonio Ielo
University of Calabria
3 shared publications - Irfan Kareem
University of Calabria
3 shared publications - Katie Gallagher
The University of Chicago
3 shared publications - Bernardo Cuteri
University of Calabria
1 shared publication
Latest Publications
- 11 October 2026
- Published by Springer Nature
- p. 117-132
BLAST: Benchmarking LLMs with ASP-Based Structured Testing
- 11 October 2026
- Published by Springer Nature
- p. 117-132
BLAST: Benchmarking LLMs with ASP-Based Structured Testing
- 11 October 2026
- Published by Springer Nature
- p. 282-297
Lightweight Language Models for Encoding ASP from Natural Language
- 11 October 2026
- Published by Springer Nature
- p. 282-297
Lightweight Language Models for Encoding ASP from Natural Language
- Open Access
- 3 November 2025
- Published by Cambridge University Press (CUP) in Theory and Practice of Logic Programming
- Vol. 26 (3-4) , 487-511
Question Answering with LLMs and Learning from Answer Sets
Large language models (LLMs) excel at understanding natural language but struggle with explicit commonsense reasoning. A recent trend of research suggests that the combination of LLM with robust symbolic reasoning systems can overcome this problem on story-based question answering (Q&A) tasks. In this setting, existing approaches typically depend on human expertise to manually craft the symbolic component. We argue, however, that this component can also be automatically learned from examples. In this work, we introduce LLM2LAS, a hybrid system that effectively combines the natural language understanding capabilities of LLMs, the rule induction power of the learning from answer sets (LAS) system ILASP, and the formal reasoning strengths of answer set programming (ASP). LLMs are used to extract semantic structures from text, which ILASP then transforms into interpretable logic rules. These rules allow an ASP solver to perform precise and consistent reasoning, enabling correct answers to previously unseen questions. Empirical results outline the strengths and weaknesses of our automatic approach for learning and reasoning in a story-based Q&A benchmark.
- 3 November 2025
- Published by Cambridge University Press (CUP) in Theory and Practice of Logic Programming
- Vol. 26 (3-4) , 487-511
Open AccessQuestion Answering with LLMs and Learning from Answer Sets
Large language models (LLMs) excel at understanding natural language but struggle with explicit commonsense reasoning. A recent trend of research suggests that the combination of LLM with robust symbolic reasoning systems can overcome this problem on story-based question answering (Q&A) tasks. In this setting, existing approaches typically depend on human expertise to manually craft the symbolic component. We argue, however, that this component can also be automatically learned from examples. In this work, we introduce LLM2LAS, a hybrid system that effectively combines the natural language understanding capabilities of LLMs, the rule induction power of the learning from answer sets (LAS) system ILASP, and the formal reasoning strengths of answer set programming (ASP). LLMs are used to extract semantic structures from text, which ILASP then transforms into interpretable logic rules. These rules allow an ASP solver to perform precise and consistent reasoning, enabling correct answers to previously unseen questions. Empirical results outline the strengths and weaknesses of our automatic approach for learning and reasoning in a story-based Q&A benchmark.
- Open Access
Question Answering with LLMs and Learning from Answer Sets
Large Language Models (LLMs) excel at understanding natural language but struggle with explicit commonsense reasoning. A recent trend of research suggests that the combination of LLM with robust symbolic reasoning systems can overcome this problem on story-based question answering tasks. In this setting, existing approaches typically depend on human expertise to manually craft the symbolic component. We argue, however, that this component can also be automatically learned from examples. In this work, we introduce LLM2LAS, a hybrid system that effectively combines the natural language understanding capabilities of LLMs, the rule induction power of the Learning from Answer Sets (LAS) system ILASP, and the formal reasoning strengths of Answer Set Programming (ASP). LLMs are used to extract semantic structures from text, which ILASP then transforms into interpretable logic rules. These rules allow an ASP solver to perform precise and consistent reasoning, enabling correct answers to previously unseen questions. Empirical results outline the strengths and weaknesses of our automatic approach for learning and reasoning in a story-based question answering benchmark.
Open AccessQuestion Answering with LLMs and Learning from Answer Sets
Large Language Models (LLMs) excel at understanding natural language but struggle with explicit commonsense reasoning. A recent trend of research suggests that the combination of LLM with robust symbolic reasoning systems can overcome this problem on story-based question answering tasks. In this setting, existing approaches typically depend on human expertise to manually craft the symbolic component. We argue, however, that this component can also be automatically learned from examples. In this work, we introduce LLM2LAS, a hybrid system that effectively combines the natural language understanding capabilities of LLMs, the rule induction power of the Learning from Answer Sets (LAS) system ILASP, and the formal reasoning strengths of Answer Set Programming (ASP). LLMs are used to extract semantic structures from text, which ILASP then transforms into interpretable logic rules. These rules allow an ASP solver to perform precise and consistent reasoning, enabling correct answers to previously unseen questions. Empirical results outline the strengths and weaknesses of our automatic approach for learning and reasoning in a story-based question answering benchmark.
- 7 May 2025
- Published by Springer Nature
- p. 1-21
Answer Set Programming and Neurosymbolic AI: Applications and Future Perspectives (Invited Talk)
- 7 May 2025
- Published by Springer Nature
- p. 1-21
Answer Set Programming and Neurosymbolic AI: Applications and Future Perspectives (Invited Talk)
- 9 October 2024
- Published by Springer Nature
- p. 112-125
Using Learning from Answer Sets for Robust Question Answering with LLM
- 9 October 2024
- Published by Springer Nature
- p. 112-125
Using Learning from Answer Sets for Robust Question Answering with LLM
- 8 May 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 229
SPARQL-QA-v2 system for Knowledge Base Question Answering
- 8 May 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 229
SPARQL-QA-v2 system for Knowledge Base Question Answering
- 19 July 2022
- Published by Springer Nature
- p. 171-184
A Neural-Machine-Translation System Resilient to Out of Vocabulary Words for Translating Natural Language to SPARQL
- 19 July 2022
- Published by Springer Nature
- p. 171-184
A Neural-Machine-Translation System Resilient to Out of Vocabulary Words for Translating Natural Language to SPARQL