The DOI matches its Crossref record; 40 of the 41 references it cites were found in a registry or an index.
Transformers as Soft Reasoners over Language
Open accessAbstract
Beginning with McCarthy's Advice Taker (1959), AI has pursued the goal of providing a system with explicit, general knowledge and having the system reason over that knowledge. However, expressing the knowledge in a formal (logical or probabilistic) representation has been a major obstacle to this research. This paper investigates a modern approach to this problem where the facts and rules are provided as natural language sentences, thus bypassing a formal representation. We train transformers to reason (or emulate reasoning) over these sentences using synthetically generated data. Our models, that we call RuleTakers, provide the first empirical demonstration that this kind of soft reasoning over language is learnable, can achieve high (99%) accuracy, and generalizes to test data requiring substantially deeper chaining than seen during training (95%+ scores). We also demonstrate that the models transfer well to two hand-authored rulebases, and to rulebases paraphrased into more natural language. These findings are significant as it suggests a new role for transformers, namely as limited "soft theorem provers" operating over explicit theories in language. This in turn suggests new possibilities for explainability, correctability, and counterfactual reasoning in question-answering.
Overview
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
Verification
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This process is algorithmic; a model that has learned a robust implementation of this algorithm should, in principle, generalize beyond the shallow depths seen in previous benchmarks (Clark et al., 2020;Tafjord et al., 2021;Saparov and He, 2023).”
From Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog (2026) · cites this paper as Clark et al., 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The PARARULE-Plus dataset [24] is a large-scale synthetic dataset for multi-step deductive reasoning over natural language, extending the original PARARULE [32] with deeper inference chains.”
From PrologMCP: A Standardized Prolog Tool Interface for LLM Agents (2026) · cites this paper as [32]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Unlike synthetically templated logic datasets (Han et al., 2022;Clark et al., 2020) in which all premises are stated as short clauses, NLR problems have explicit statements along with implicit information that must be inferred from common sense and context.”
From Reliable Reasoning Beyond Natural Language (2024) · cites this paper as Clark et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“Navigate, like many other benchmark datasets such as RuleTaker (Clark et al., 2020), is systematically generated.”
From Reliable Reasoning Beyond Natural Language (2024) · cites this paper as Clark et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“These benchmarks revealed that models at the time struggle as proof depth increases, but the depths studied remain shallow.”
From Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog (2026) · cites this paper as Clark et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“Early work on deductive reasoning benchmarks such as RuleTaker (Clark et al., 2020) and ProofWriter (Tafjord et al., 2021) established the basic setup of query answering over sets of rules and facts, with ProofWriter reaching a maximum proof depth of five steps.ProntoQA (Saparov and He, 2023) introduces proof-structure controls and formal error attribution, also evaluated up to five hops.”
From Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog (2026) · cites this paper as Clark et al., 2020
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208
ASH, R. B. (1966) · Cited by 3,990
NIPS 2016 Tutorial: Generative Adversarial NetworksPreprint
Goodfellow, I. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.00160 · Cited by 2,048
A Decomposable Attention Model for Natural Language Inference
Parikh, A. P., Täckström, O., Das, D., & Uszkoreit, J. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1244 · Cited by 1,351
Enhanced LSTM for Natural Language Inference
Chen, Q., Zhu, X., Ling, Z.-H., Wei, S., Jiang, H., & Inkpen, D. Z. (2017) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p17-1152 · Cited by 1,315
Towards a Theory of Declarative Knowledge
Apt, K. R., Blair, H. A., & Walker, A. (1988) · Foundations of Deductive Databases and Logic Programming · doi:10.1016/b978-0-934613-40-8.50006-3 · Cited by 1,151
Applications of circumscription to formalizing common-sense knowledge
McCarthy, J. (1986) · Artificial Intelligence · doi:10.1016/0004-3702(86)90032-9 · Cited by 1,114
RACE: Large-scale ReAding Comprehension Dataset From Examinations
Lai, G., Xie, Q., Liu, H., Yang, Y., & Hovy, E. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1082 · Cited by 1,044
The logic theory machine-A complex information processing system
Newell, A., & Simon, H. (1956) · IEEE Transactions on Information Theory · doi:10.1109/tit.1956.1056797 · Cited by 846
Flagged first, then by citations
1 of the 41 references couldn’t be matched to a known paper.
Research works printed but not linked: 5
- [Abdelaziz et al. , 2020] Ibrahim Abdelaziz, Veronika Thost, Maxwell Crouse, and Achille Fokoue. An experimental study of formula embeddings for automated theorem proving in first-order logic. arXiv , 2002.00423, 2020. · arXiv
- [Richardson and Sabharwal, 2019] Kyle Richardson and Ashish Sabharwal. What does my qa model know? devising controlled probes using expert knowledge. ArXiv , abs/1912.13337, 2019. · arXiv
- [Saxton et al. , 2019] David Saxton, Edward Grefenstette, Felix Hill, and Pushmeet Kohli. Analysing mathematical reasoning abilities of neural models. In ICLR , 2019.
- [Selsam et al. , 2019] Daniel Selsam, Matthew Lamm, Benedikt B¨ unz, Percy Liang, Leonardo de Moura, and David L. Dill. Learning a SAT solver from single-bit supervision. In ICLR , 2019.
- [Talmor et al. , 2019] A. Talmor, Y. Elazar, Y. Goldberg, and J. Berant. oLMpics - on what language model pre-training captures. ArXiv , abs/1912.13283, 2019. · arXiv
Cited by
Sorted by citations
Items 101–191 of 191
Schockaert, S. (2023) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2023.108981 · Cited by 5
MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure
Huang, Y., Zhang, H., Hong, R., Liang, X., Zhang, C., & Yu, D. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.310 · Cited by 5
Probabilistic Graph Reasoning for Natural Proof Generation
Sun, C., Zhang, X., Chen, J., Gan, C., Wu, Y., Chen, J., Zhou, H., & Li, L. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.277 · Cited by 6
GLUECons: A Generic Benchmark for Learning under Constraints
Faghihi, H. R., Nafar, A., Chen, Z., Mirzaee, R., Zhang, Y., Uszok, A., Wan, A., Premsri, T., Roth, D., & Kordjamshidi, P. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i8.26143 · Cited by 7
APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning
Sanyal, S., Yi‐chong, X., Wang, S., Yang, Z., Pryzant, R., Yu, W., Zhu, C., & Ren, X. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.347 · Cited by 7
Jansen, P. A., Smith, K. J., Moreno, D., & Ortiz, H. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.596 · Cited by 8
Natural Language QA Approaches using Reasoning with External KnowledgePreprint
Baral, C. R., Banerjee, P., Pal, K. K., & Mitra, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03446 · Cited by 5
ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains
Zhu, M., Weng, Y., He, S., Liu, K., & Zhao, J. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055048 · Cited by 4
Can Transformers Reason in Fragments of Natural Language?
Schlegel, V., Pavlov, K. V., & Pratt-Hartmann, I. E. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.768 · Cited by 7
From Chat to Publication Management: Organizing your related work using BibSonomy & LLMs
Völker, T., Pfister, J., Koopmann, T., & Andreas Hotho, A. (2024) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3627508.3638298 · Cited by 4
Dyna-bAbI: unlocking bAbI’s potential with dynamic synthetic benchmarking
Tamari, R., Richardson, K., Kahlon, N., Sar-Shalom, A., Liu, N. F., Tsarfaty, R., & Shahaf, D. (2022) · Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/2022.starsem-1.9 · Cited by 5
Self-citationCALM-Bench: A Multi-task Benchmark for Evaluating Causality-Aware Language Models
Dalal, D., Buitelaar, P., & Arčan, M. (2023) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2023.findings-eacl.23 · Cited by 5
Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?
Kudo, K., Aoki, Y., Kuribayashi, T., Brassard, A., Yoshikawa, M., Sakaguchi, K., & Inui, K. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.98 · Cited by 5
Constrained Fact Verification for FEVER
Pratapa, A., Jayanthi, S. M., & Nerella, K. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.629 · Cited by 5
Can Transformers Reason About Effects of Actions?Preprint
Banerjee, P., Baral, C. R., Luo, M., Mitra, A., Pal, K. K., Son, T. C., & Varshney, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.09938 · Cited by 4
Learning to Solve Complex Tasks by Talking to Agents.Preprint
Khot, T., Richardson, K., Khashabi, D., & Sabharwal, A. (2021) · arXiv (Cornell University) · Cited by 4
Self-citationReliable Reasoning Beyond Natural Language
Borazjanizadeh, N., & Piantadosi, S. T. (2024) · arXiv · doi:10.48550/arxiv.2407.11373 · Cited by 3
“…generated, where the problem statements lack diversity in the wording, and premises and conclusions are expressed in short, direct statements [16, 10], our problems necessitate richer natural language understanding and both implicit and explicit deductive reasoning for resolution (see e.g. Table…”
InfluentialBetz, G., & Richardson, K. (2023) · PLoS ONE · doi:10.1371/journal.pone.0281372 · Cited by 6
Self-citationMeadows, J., & Freitas, A. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00594 · Cited by 30
Towards General Natural Language Understanding with Probabilistic Worldbuilding
Saparov, A., & Mitchell, T. M. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00463 · Cited by 6
Porada, I., Sordoni, A., & Cheung, J. C. K. (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.337 · Cited by 6
Knowledge Acquired by Foundation Models
Paaß, G., & Giesselbach, S. (2023) · Artificial intelligence: foundations, theory, and algorithms/Artificial intelligence: Foundations, theory, and algorithms · doi:10.1007/978-3-031-23190-2_4 · Cited by 3
LogicNMR: Probing the Non-monotonic Reasoning Ability of Pre-trained Language Models
Xiu, Y., Xiao, Z., & Liu, Y. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.265 · Cited by 3
A multi-source heterogeneous knowledge injected prompt learning method for legal charge prediction
Sun, J., & Wei, C. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113438 · Cited by 5
Modelling Symbolic Knowledge Using Neural Representations
Schockaert, S., & Gutiérrez-Basulto, V. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-95481-9_3 · Cited by 3
Hey AI, Can You Solve Complex Tasks by Talking to Agents?
Khot, T., Richardson, K., Khashabi, D., & Sabharwal, A. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.142 · Cited by 13
Self-citationDesign Neural Database to identify the problem of the conditions in Dental Clinics
Talib, R., Rashid, S. T., Jumaah, N. S., & Sabah, R. (2022) · Al-Salam Journal for Engineering and Technology · doi:10.55145/ajest.2022.01.02.001 · Cited by 3
Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference
Thayaparan, M., Valentino, M., Ferreira, D. M., Rozanova, J., & Freitas, A. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00508 · Cited by 3
Cross-Domain Reasoning via Template Filling.Preprint
Rajagopal, D., Khetan, V., Sacaleanu, B., Gershman, A. V., Fano, A., & Hovy, E. H. (2021) · arXiv (Cornell University) · Cited by 3
Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models
Pirozelli, P., José, M. M., Filho, P. D. T. P. D. C., Brandão, A. A. F., & Cozman, F. G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71167-1_2 · Cited by 5
Cost-Effective Knowledge Graph Reasoning for Complex Factoid Questions
Yang, X., Chiang, M.-F., Lee, W.-C., & Chang, Y. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533753 · Cited by 2
Betz, G., & Richardson, K. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.900943 · Cited by 2
Self-citationAssessing Step-by-Step Reasoning against Lexical Negation: A Case Study on Syllogism
Ye, M., Kuribayashi, T., Suzuki, J., Kobayashi, G., & Funayama, H. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.912 · Cited by 4
Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention
Foroutan, N., Banaei, M., Aberer, K., & Bosselut, A. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.632 · Cited by 5
Bao, Q., Gendron, G., Peng, A. Y., Zhong, W., Tan, N. Ö., Chen, Y., Witbrock, M., & Liu, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6603-4_22 · Cited by 17
Question Classification for Efficient QA System
Moholkar, E. A. K. P. (2021) · Türk bilgisayar ve matematik eğitimi dergisi · doi:10.17762/turcomat.v12i2.1526 · Cited by 3
Identifying the limits of transformers when performing model-checking with natural language
Madusanka, T., Batista-Navarro, R., & Pratt-Hartmann, I. E. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.257 · Cited by 5
Madusanka, T., Zahid, I., Li, H., Pratt-Hartmann, I. E., & Batista-Navarro, R. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.536 · Cited by 3
Logical Reasoning for Task Oriented Dialogue Systems
Beygi, S., Fazel-Zarandi, M., Cervone, A., Krishnan, P., & Jonnalagadda, S. (2022) · Workshop on e-Commerce and NLP (ECNLP) · doi:10.18653/v1/2022.ecnlp-1.10 · Cited by 2
PrologMCP: A Standardized Prolog Tool Interface for LLM Agents
Mensfelt, A., Prabhakaran, A., Haret, A., Trencsenyi, V., & Stathis, K. (2026) · arXiv · doi:10.48550/arxiv.2606.14935 · Cited by 1
Toward Enhancing Reasoning Capabilities of LLMs: An Approach via Synthetic Logic Corpus
Morishita, T., Morio, G., Yamaguchi, A., & Sogawa, Y. (2025) · Journal of Natural Language Processing · doi:10.5715/jnlp.32.520 · Cited by 1
Think straight or think again? Continual joint learning of deduction, abduction and induction
Xiong, K., Ding, X., Cao, Y., Zhao, Y., Liu, T., & Qin, B. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107768 · Cited by 1
Large Language Model for OWL Proofs
Yang, H., Chen, J., & Sattler, U. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792395 · Cited by 4
Logically Consistent Adversarial Attacks for Soft Theorem Provers
Gaskell, A., Miao, Y., Toni, F., & Specia, L. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/573 · Cited by 1
Investigating Transformer-Guided Chaining for Interpretable Natural Logic Reasoning
Kanagasabai, R., Rajamanickam, S., & Shi, W. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.588 · Cited by 1
MTR: A Dataset Fusing Inductive, Deductive, and Defeasible Reasoning
Li, Y., Tian, J., Fan, C., Chen, W., He, H., & Jin, Y. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.640 · Cited by 1
Probing Pretrained Language Models with Hierarchy Properties
Lovón-Melgarejo, J., Moreno, J. G., Besançon, R., Ferret, O., & Tamine, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56060-6_9 · Cited by 1
Transformers in the Service of Description Logic-Based Contexts
Poulis, A., Tsalapati, E., & Koubarakis, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-77792-9_20 · Cited by 1
Advances in reasoning by prompting large language models: A survey
Hong, R., Pang, X., & Zhang, C. (2026) · Cybernetics and Intelligence · doi:10.26599/cai.2024.9390004 · Cited by 3
BiQuAD: Towards QA based on deeper text understanding
Grimm, F., & Cimiano, P. (2021) · Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/2021.starsem-1.10 · Cited by 1
AnaLog: Testing Analytical and Deductive Logic Learnability in Language Models
Ryb, S., Giulianelli, M., Sinclair, A., & Fernández, R. (2022) · Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/2022.starsem-1.5 · Cited by 1
Evaluating and Improving the Reasoning Abilities of Language Models
Helwe, C. (2024) · theses.fr (ABES) · doi:10.70675/7fc70e59zdd27z4b0fza38dz03a2c67cda50 · Cited by 1
Evaluation and Integration of Structural Knowledge for Pre-trained Language Models
Lovón-Melgarejo, J. (2024) · theses.fr (ABES) · doi:10.70675/9b2d6bf6za13az4dfcza45bzca75ad5b25a6 · Cited by 1
Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog
Al-Negheimish, H., Ilieva, J., & Kim, Y. (2026) · arXiv · doi:10.48550/arxiv.2610.11592
“This process is algorithmic; a model that has learned a robust implementation of this algorithm should, in principle, generalize beyond the shallow depths seen in previous benchmarks (Clark et al., 2020; Tafjord et al., 2021; Saparov and He, 2023).”
Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
György, A., Lattimore, T., Lazić, N., & Szepesvári, C. (2025) · arXiv · doi:10.48550/arxiv.2506.23908
Pre-trained Language Models as Symbolic Reasoners over Knowledge?Preprint
Kassner, N., Kroje, B., & Schütze, H. (2020) · arXiv (Cornell University)
Hacking with God: a Common Programming Language of Robopsychology and RobophilosophyPreprint
Bátfai, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09068 · Cited by 3
Liang, Z., & Surdeanu, M. (2020) · Workshop on Insights from Negative Results in NLP (Insights) · doi:10.18653/v1/2020.insights-1.12
Abstraction, Reasoning and Deep Learning: A Study of the "Look and Say" Sequence
Zadrozny, W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.12755
Neural Unification for Logic Reasoning over Natural LanguagePreprint
Picco, G., Lam, H. T., Sbodio, M. L., & Garcia, V. L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.08460 · Cited by 1
Formulating critical questions to the user in the course of decision-making
Galitsky, B. A. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-824521-7.00007-7
CSKE: Commonsense Knowledge Enhanced Text Extension Framework for Text-Based Logical Reasoning
Zeng, Y., Ding, X., Du, L., Liu, T., & Qin, B. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7596-7_9
Embedding Contextual Information in Seq2seq Models for Grounded Semantic Role Labeling
Hromei, C. D., Cristofori, L., Croce, D., & Basili, R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-27181-6_33
Exploring the Capacity of Pretrained Language Models for Reasoning about Actions and Change
He, W., Huang, C., Xiao, Z., & Liu, Y. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.255
The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources
Arodi, A., Pömsl, M., Suleman, K., Trischler, A., Olteanu, A., & Cheung, J. C. K. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.841 · Cited by 1
ProofInfer: Generating Proof via Iterative Hierarchical Inference
Fei, Z., Zhang, Q., Zhou, X., Gui, T., & Huang, X. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.747
Natural Language Annotations for Reasoning about Program Semantics
Zocca, M. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.601
Ghosal, D., Aditya, S., & Choudhury, M. (2023) · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · doi:10.18653/v1/2023.ijcnlp-main.56
Wiegel, N. L., & Mettini, E. (2024) · Russian Journal of Philosophical Sciences · doi:10.30727/0235-1188-2024-67-1-29-53
Targeted training for numerical reasoning with large language models
Xiao, L., Liu, S., Zhu, Y., & Gong, C. B. (2024) · Knowledge and Information Systems · doi:10.1007/s10115-024-02216-1
Reasoning in Transformers – Mitigating Spurious Correlations and Reasoning Shortcuts
Enström, D., Kjellberg, V., & Johansson, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71170-1_18
Assessing the Syllogistic Logic and Fact-Checking Capabilities of Large Language Models
Solorzano, C. D., Delaflor, M., & Toxtli, C. (2024) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics62450.2024.00094
Leveraging Semantic Parsing using Text Embeddings and Reinforcement Learning
Piza-Londoño, J., & Andrade-Lotero, E. J. (2024) · IEEE Latin American Conference on Computational Intelligence (LA-CCI) · doi:10.1109/la-cci62337.2024.10814850
Enhancing logical reasoning in language models: An investigation of the Capybara dataset
Guerrero, L. E. M., Ceballos, Y. F., & Rojas, L. D. T. (2025) · Contemporary Educational Technology · doi:10.30935/cedtech/16425
Type-agnostic and form-oriented deductive conclusion generation
Wu, X., Bu, Y., Cai, Y., Chen, Y., & Leung, H.-F. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107968
Combined GNN specialized in inductive prediction and PLM for natural language inductive reasoning
Tomei, K., & Hagiwara, M. (2025) · Journal of Intelligent Information Systems · doi:10.1007/s10844-025-00979-9 · Cited by 1
Rule2Text: Natural Language Explanation of Logical Rules in Knowledge Graphs
Shirvani-Mahdavi, N., Wingfield, D., Ghasemi, A., & Li, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-08887-1_7
SWInG: A SemanticWeb Integrated with Generative AI Architecture for Dynamic Data Generation
de Freitas, W. L. C. G., & da Silva, J. R. (2025) · Simpósio Brasileiro de Jogos e Entretenimento Digital (SBGames) · doi:10.5753/sbgames.2025.10018
Thai Fake News Detection with LLM Integration for Web Application
Chansawang, N., Aueamornsuk, S., Phunmongkon, T., & Tarnpradab, S. (2025) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse67377.2025.11297909
Towards Explainable Educational QA: A Chain-of-Thought and Retrieval-Augmented Approach
Tinh, T. V., Dang, D., Tran, M. Q., Tong, D. K. H., Nguyen, N.-K., Dinh, H., & Duong, V.-H. (2025) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf68649.2025.11365254
Next-Gen Theorem Proving: A Multi-Agent Paradigm for Automated Reasoning
Chigullapally, A. G., Dantu, R., Zaman, S., & Pokharel, A. (2025) · IEEE International Conference on Cognitive Machine Intelligence (CogMI) · doi:10.1109/cogmi67134.2025.00013
Analysis of Semantic Communication for Logic-based Hypothesis Deduction
Saz, A. F., Xiong, S., & Fekri, F. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432447
A Multi-Stage Neuro-Symbolic Framework for Trustworthy Agentic Intelligence in ICE Systems
Pei, J., Feng, M., Xiu, Y., Gulzar, Y., Alsisi, R. H., & Dai, M. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3676046
A framework for the continuous curation of a knowledge base system
Ahmadi, N. (2021) · theses.fr (ABES) · doi:10.70675/7f54e1cez3f33z4329z8915z355f69842034
Employing Transformers and Humans for Textual-Claim Verification
Saeed, M. (2022) · theses.fr (ABES) · doi:10.70675/3e02a3a6z8281z4d84z8f38ze617eaaf969b
SoGRE: Boosting Logical Reasoning of LLMs via Solver-Guided Reasoning Enhancement
Wang, Z., Zhang, L., Zhang, M., Li, Q. P., & Zhang, M. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463079
Morishita, T. (2026) · Journal of Natural Language Processing · doi:10.5715/jnlp.33.1033
Neurosymbolic Large Language Models: A Survey of Symbolic Integration, Reasoning and Explainability
Rani, M., Mishra, B. K., & Thakker, D. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10794-4 · Cited by 2
Xu, S., & Asadinia, M. (2026) · IEEE International Conference on Omni-layer Intelligent Systems (COINS) · doi:10.1109/coins69995.2026.11715614
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Georgiev, P., Lei, V. I., Burnell, R., Bai, L., Gulati, A., Tanzer, G., Vincent, D., Pan, Z., Wang, S., et al. (2024) · arXiv · doi:10.48550/arxiv.2403.05530 · Cited by 306
Metadata
- Authors
- Clark, P., Tafjord, O., & Richardson, K.
- Affiliations
- Allen Institute for Artificial Intelligence (US)
- Venue
- Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
- Published
- 2020-07
- Pages
- 3882-3890
- OpenAlex
- W3006188107
- Cited by
- 176
- References
- 41
- Citations by year
- 2026: 8 · 2025: 19 · 2024: 15 · 2023: 41 · 2022: 37 · 2021: 37 · 2020: 18
- FWCI
- 12.69
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- natural language reasoning, transformer models, synthetic training data, rule-based reasoning, knowledge representation, theorem proving, question answering, explainability, counterfactual reasoning, knowledge distillation
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
