Reliable Natural Language Understanding with Large Language Models and Answer Set Programming
Open accessAbstract
Humans understand language by extracting information (meaning) from sentences, combining it with existing commonsense knowledge, and then performing reasoning to draw conclusions.While large language models (LLMs) such as GPT-3 and ChatGPT are able to leverage patterns in the text to solve a variety of NLP tasks, they fall short in problems that require reasoning.They also cannot reliably explain the answers generated for a given question.In order to emulate humans better, we propose STAR, a framework that combines LLMs with Answer Set Programming (ASP).We show how LLMs can be used to effectively extract knowledge-represented as predicates-from language.Goal-directed ASP is then employed to reliably reason over this knowledge.We apply the STAR framework to three different NLU tasks requiring reasoning: qualitative reasoning, mathematical reasoning, and goal-directed conversation.Our experiments reveal that STAR is able to bridge the gap of reasoning in NLU tasks, leading to significant performance improvements, especially for smaller LLMs, i.e., LLMs with a smaller number of parameters.NLU applications developed using the STAR framework are also explainable: along with the predicates generated, a justification in the form of a proof tree can be produced for a given output.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Using traditional machine learning algorithms to supplement a logic program increases explainability while utilizing the benefits of deep learning and other machine learning models.
“This approach increases explainability while utilizing the benefits of deep learning and other machine learning models, such as in the paper by Rajasekharan et al. that uses an s(CASP) knowledge base to constrain an LLM into providing more reliable results [14].”
From Autonomous Task Completion Based on Goal-directed Answer Set Programming (2025) · cites this paper as [14]
The Related Work section says the approach combines LLM predicate extraction with s(CASP) reasoning, and that the explicit reasoning is more reliable and explainable. The Introduction also says s(CASP) can provide proof-tree justifications. The paper does not describe the knowledge base as constraining the LLM itself; it assigns reasoning to s(CASP) after the LLM extracts predicates. Page numbers are unavailable in our copy. (LLM, conf=0.84)
Experimental — accuracy not yet measuredAn s(CASP) knowledge base can constrain an LLM into providing more reliable results.
“This approach increases explainability while utilizing the benefits of deep learning and other machine learning models, such as in the paper by Rajasekharan et al. that uses an s(CASP) knowledge base to constrain an LLM into providing more reliable results [14].”
From Autonomous Task Completion Based on Goal-directed Answer Set Programming (2025) · cites this paper as [14]
The Introduction describes combining LLM-generated predicates with ASP-coded commonsense knowledge to produce reliable responses. But the Related Work section explicitly separates the components: the LLM extracts predicates, while s(CASP) performs the reasoning. The paper therefore supports improved reliability through the combined system, not the claim that the knowledge base constrains the LLM itself. (LLM, conf=0.86)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Suspending OpenMP Tasks on Asynchronous Events: Extending the Taskwait Construct
Pereira, R., Martin, M., Roussel, A., Carribault, P., & Gautier, T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-40744-4_5 · Cited by 13,143 · see citing works
The Stanford CoreNLP Natural Language Processing Toolkit
Manning, C. D., Surdeanu, M., Bauer, J., Finkel, J. R., Bethard, S. J., & McClosky, D. (2014) · Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL Demo) · doi:10.3115/v1/p14-5010 · Cited by 7,171 · see citing works
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263 · see citing works
GPT-3: Its Nature, Scope, Limits, and Consequences
Floridi, L., & Chiriatti, M. (2020) · Minds and Machines · doi:10.1007/s11023-020-09548-1 · Cited by 2,519 · see citing works
Evaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436 · see citing works
Answer set programming at a glance
Brewka, G., Eiter, T., & Truszczyński, M. (2011) · Communications of the ACM · doi:10.1145/2043174.2043195 · Cited by 946 · see citing works
MasakhaNER: Named Entity Recognition for African Languages
Adelani, D. I., Abbott, J., Neubig, G., D’souza, D., Kreutzer, J., Lignos, C., Palen-Michel, C., Buzaaba, H., Rijhwani, S., Ruder, S., et al. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00416 · Cited by 277 · see citing works
The E2E Dataset: New Challenges For End-to-End Generation
Novikova, J., Dušek, O., & Rieser, V. (2017) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/w17-5525 · Cited by 275 · see citing works
Gelfond, M., & Kahl, Y. (2014) · doi:10.1017/cbo9781139342124 · Cited by 253 · see citing works
Parsing Algebraic Word Problems into Equations
Koncel-Kedziorski, R., Hajishirzi, H., Sabharwal, A., Etzioni, O., & Ang, S. D. (2015) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00160 · Cited by 233 · see citing works
(2022) · doi:10.52202/068431-1126 · Cited by 182 · see citing works
STaR: Bootstrapping Reasoning With Reasoning
Zelikman, E., Wu, Y., Mu, J., & Goodman, N. D. (2022) · arXiv · doi:10.48550/arxiv.2203.14465 · Cited by 182 · see citing works
PAL: Program-aided Language Models
Gao, L., Madaan, A., Zhou, S., Alon, U., Liu, P., Yang, Y., Callan, J., & Neubig, G. (2022) · arXiv · doi:10.48550/arxiv.2211.10435 · Cited by 155 · see citing works
NeurASP: Embracing Neural Networks into Answer Set Programming
Yang, Z., Ishay, A., & Lee, J. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/243 · Cited by 128 · see citing works
Chen, W., Ma, X., Wang, X., & Cohen, W. W. (2022) · arXiv · doi:10.48550/arxiv.2211.12588 · Cited by 125 · see citing works
Is neuro-symbolic AI meeting its promises in natural language processing? A structured review
Hamilton, K., Nayak, A., Božić, B., & Longo, L. (2022) · Semantic Web · doi:10.3233/sw-223228 · Cited by 97 · see citing works
Riegel, R., Gray, A., Luus, F., Khan, N., Makondo, N., Akhalwaya, I. Y., Qian, H., Fagin, R., Barahona, F., Sharma, U., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.13155 · Cited by 95 · see citing works
Constraint Answer Set Programming without Grounding
ARIAS, J., CARRO, M., SALAZAR, E., MARPLE, K., & GUPTA, G. (2018) · Theory and Practice of Logic Programming · doi:10.1017/s1471068418000285 · Cited by 88 · see citing works
Self-citationA Physician Advisory System for Chronic Heart Failure management based on knowledge patterns
CHEN, Z., MARPLE, K., SALAZAR, E., GUPTA, G., & Tamil, L. S. (2016) · Theory and Practice of Logic Programming · doi:10.1017/s1471068416000429 · Cited by 73 · see citing works
Self-citationPre-trained transformers: an empirical comparison
Casola, S., Lauriola, I., & Lavelli, A. (2022) · Machine Learning with Applications · doi:10.1016/j.mlwa.2022.100334 · Cited by 66 · see citing works
Few-Shot Semantic Parsing with Language Models Trained on Code
Shin, R., & Durme, B. V. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.396 · Cited by 38 · see citing works
Justifications for Goal-Directed Constraint Answer Set Programming
Arias, J., Carro, M., Chen, Z., & Gupta, G. (2020) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.325.12 · Cited by 34 · see citing works
Self-citationAQuA: ASP-Based Visual Question Answering
Basu, K., Shakerin, F., & Gupta, G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-39197-3_4 · Cited by 28 · see citing works
Self-citationAutomated Interactive Domain-Specific Conversational Agents that Understand Human Dialogs
Zeng, Y., Rajasekharan, A., Padalkar, P., Basu, K., Arias, J., & Gupta, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-52038-9_13 · Cited by 16 · see citing works
Self-citationAUTO-DISCERN: Autonomous Driving Using Common Sense ReasoningPreprint
Kothawade, S. N., Khandelwal, V., Basu, K., Wang, H., & Gupta, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.13606 · Cited by 13 · see citing works
Self-citationJury-Trial Story Construction and Analysis Using Goal-Directed Answer Set Programming
Xu, Z., Arias, J., Salazar, E., Chen, Z., Varanasi, S. C., Basu, K., & Gupta, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-24841-2_17 · Cited by 6 · see citing works
Self-citationCASPR: A Commonsense Reasoning-based Conversational SocialbotPreprint
Basu, K., Wang, H., Dominguez, N., Li, X., Li, F., Varanasi, S. C., & Gupta, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.05387 · Cited by 6 · see citing works
Self-citationQUAREL: A Dataset and Models for Answering Questions about Qualitative Relationships
Tafjord, O., Clark, P. E., Gardner, M., Yih, W.-T., & Sabharwal, A. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33017063 · Cited by 5 · see citing works
Knowledge-driven Natural Language Understanding of English Text and its Applications
Basu, K., Varanasi, S. C., Shakerin, F., Arias, J., & Gupta, G. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i14.17488 · Cited by 4 · see citing works
Self-citationRestKB: A Library of Commonsense Knowledge about Dining at a Restaurant
Inclezan, D. (2019) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.306.19 · Cited by 3 · see citing works
Chan, S., & Cheney, J. (2020) · International Symposium on Practical Aspects of Declarative Languages · doi:10.1007/978-3-030-39197-3
Flagged first, then by citations
Research works printed but not linked: 1
- Tom Brown, Benjamin Mann & Others (2020): Language Models are Few-Shot Learners. In: NeurIPS, 33, Curran Associates, Inc., pp. 1877-1901, doi:10.5555/3495724.3495883. · DOI
Cited by
Sorted by citations
Tihanyi, N., Charalambous, Y., Jain, R., Ferrag, M. A., & Cordeiro, L. C. (2025) · International Conference/Workshop on Automation of Software Test · doi:10.1109/ast66626.2025.00020 · Cited by 72 · see citing works
On the Use of Neurosymbolic AI for Defending Against Cyber Attacks
Grov, G., Halvorsen, J., Eckhoff, M. W., Hansen, B. J., Eian, M., & Mavroeidis, V. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71167-1_7 · Cited by 12 · see citing works
Mishra, V., Saxena, D., Gupta, K., Patni, S., & Singh, A. K. (2025) · Scientific Reports · doi:10.1038/s41598-025-17937-8 · Cited by 10 · see citing works
Neuro-Symbolic Computing: Advancements and Challenges in Hardware–Software Co-Design
Yang, X., Wang, Z., Hu, X. S., Kim, C. H., Yu, S., Pajić, M., Manohar, R., Chen, Y., & Li, H. H. (2023) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2023.3336251 · Cited by 9 · see citing works
Relational Programming with Foundational Models
Li, Z., Huang, J., Liu, J., Zhu, F., Zhao, E., Dodds, W., Velingker, N., Rajeev Alur, A., & Naik, M. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i9.28934 · Cited by 6 · see citing works
Deep Fake and Digital Forensics
Alshammari, H., & Elleithy, K. M. (2023) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon59035.2023.10315974 · Cited by 5 · see citing works
Wang, X., Dai, C., & Bao, L. (2025) · Information Discovery and Delivery · doi:10.1108/idd-05-2024-0072 · Cited by 5 · see citing works
Leveraging Generative AI for Enhanced Predictive Maintenance and Anomaly Detection in Manufacturing
Mugala, V. S. (2025) · Information systems engineering and management · doi:10.1007/978-3-031-76710-4_13 · Cited by 5 · see citing works
Wang, C. C., Li, Z., Chen, T., Wang, R., & Ju, Z. (2023) · Electronics · doi:10.3390/electronics12163391 · Cited by 5 · see citing works
Visual Graph Question Answering with ASP and LLMs for Language Parsing
Bauer, J. J., Eiter, T., Higuera, N., & Oetsch, J. (2025) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.416.2 · Cited by 4 · see citing works
Automated Theorem Provers Help Improve Large Language Model Reasoning
McGinness, L. P., & Baumgartner, P. (2024) · EPiC series in computing · doi:10.29007/2n9m · Cited by 4 · see citing works
LLM+Reasoning+Planning for Supporting Incomplete User Queries in Presence of APIs
Agarwal, S., Sreepathy, A., Alonso, D., & Lamba, P. (2025) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.416.3 · Cited by 3 · see citing works
TIC: Translate-Infer-Compile for Accurate “Text to Plan” Using LLMs and Logical Representations
Agarwal, S., & Sreepathy, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71170-1_19 · Cited by 3 · see citing works
Experimenting with Neurosymbolic Artificial Intelligence for Defending Against Cyber Attacks
Eckhoff, M. W., Halvorsen, J., Hansen, B. J., Eian, M., Mavroeidis, V., Chetwyn, R. A., Skjøtskift, G., & Grov, G. (2025) · Neurosymbolic Artificial Intelligence · doi:10.1177/29498732251377352 · Cited by 2 · see citing works
Transforming Natural Language Requirements to Formalism Using LLMs
Meng, B., Lorch, R., Siu, K., Durling, M., Varanasi, S. C., Paul, S., & Moitra, A. (2025) · Systems Engineering · doi:10.1002/sys.70023 · Cited by 1 · see citing works
Yadav, I., Schindler, S., Peters, D., & Klinger, R. (2026) · Semantic Web · doi:10.1177/22104968261453132 · Cited by 1 · see citing works
Autonomous Task Completion Based on Goal-directed Answer Set Programming
Tudor, A. R. (2025) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.416.39
Alviano, M., Capalbo, M., Gottlob, G., Grillo, L., Kareem, I., Lo Scudo, F., Piccolo, S. A., & Rodriguez Reiners, L. A. (2026) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.21678
“More broadly, LLMs have become standard tools for translating natural language into ASP or other logic-based representations amenable to symbolic inference (Kaur et al. 2025; Rajasekharan et al. 2023; Z. Wang et al. 2024; Yang et al. 2024).”
Full-Stack Collaboration for Robust Heterogeneity-Enabled AI Systems
Qiu, Y. (2024) · ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity (SPLASH) · doi:10.1145/3689491.3691817
Enhanced Question Answering System through URL based Data ExtractionPreprint
Priya, C. G., Noori, V. K. A., Reddy, U. H., Kumar, S. M., & Pradeepthi, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5066794
Reliable Conversational Agents under ASP Control that Understand Natural Language
Zeng, Y. (2025) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.416.41
Self-citationMinimal reduct for propositional circumscription
Xie, Z.-T., Wang, Y., Yang, L., & Feng, R. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1614894
Fine-tuning LLMs for answer set programming
Coppolillo, E., Calimeri, F., Manco, G., Perri, S., & Ricca, F. (2026) · Journal of Intelligent Information Systems · doi:10.1007/s10844-025-01017-4
Logic-Guided Data Extraction with Answer Set Programming and Large Language Models
Alviano, M., Grillo, L., Leone, N., & Scudo, F. L. (2026) · Theory and Practice of Logic Programming · doi:10.1017/s1471068426100635
Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering
Higuera, N., Oetsch, J., & Eiter, T. (2026) · Theory and Practice of Logic Programming · doi:10.1017/s1471068426100684
An LLM-Based Approach for Creating Multi-agent Systems
Rezunik, L., Alexandrov, D., & Prozorskiy, M. A. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-04186-9_8
BLAST: Benchmarking LLMs with ASP-Based Structured Testing
Borroto, M., Coppolillo, E., Calimeri, F., Manco, G., Perri, S., & Ricca, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38320-4_8
- Authors
- Rajasekharan, A., Zeng, Y., Padalkar, P., & Gupta, G.
- Affiliations
- The University of Texas at Dallas (US)
- Venue
- Electronic Proceedings in Theoretical Computer Science
- Publisher
- Open Publishing Association
- Published
- 2023-09-12
- Volume
- 385
- Pages
- 274-287
- ISSN
- 2075-2180 (ISSN-L)
- OpenAlex
- W4386211255
- Cited by
- 26
- References
- 30
- Citations by year
- 2026: 6 · 2025: 12 · 2024: 5 · 2023: 3
- FWCI
- 2.30
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by-nc-nd
- Locations
- Electronic Proceedings in Theoretical Computer Science (publishedVersion, cc-by-nc-nd)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1910131, 1916206)
- University of Texas at Dallas
- Defense Advanced Research Projects Agency
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- natural language understanding, large language models, answer set programming, goal-directed reasoning, knowledge extraction from text, commonsense reasoning, qualitative reasoning, mathematical reasoning, explainable reasoning, proof trees, STAR framework
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
