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.
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?
A model that has learned a robust implementation of the proof-tree tracing algorithm should, in principle, generalize beyond the shallow depths seen in previous benchmarks.
“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
Section 4.2 (p. 4) reports that a model trained on problems up to depth 3 generalized to depth-5 problems, supporting the point about reasoning beyond shallower training depths. But Section 2 (p. 2) says the authors impose no structure on the neural reasoning process; the paper does not establish that the model learned a proof-tree tracing algorithm. (LLM, conf=0.82)
Experimental — accuracy not yet measuredThe PARARULE-Plus dataset is a large-scale synthetic dataset for multi-step deductive reasoning over natural language, extending the original PARARULE with deeper inference chains.
“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]
Dataset Generation (p. 6) describes a 40,000-question ParaRules dataset with questions at multiple inference depths, supporting the large-scale, multi-step reasoning description. But our copy calls it ParaRules, not ParaRules-Plus, and does not describe a Plus dataset extending an original with deeper inference chains. Section 4.4 (p. 6) also cautions that its paraphrased rules do not test arbitrary natural language. (LLM, conf=0.84)
Experimental — accuracy not yet measuredUnlike synthetically templated logic datasets, NLR problems have explicit statements along with implicit information that must be inferred from common sense and context.
“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
Navigate, like many other benchmark datasets such as RuleTaker, is systematically generated.
“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
These previous benchmarks revealed that models at the time struggle as proof depth increases, but the depths studied remain shallow.
“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
Previous deductive reasoning benchmarks such as RuleTaker, ProofWriter, and ProntoQA studied proof depths up to five steps or hops.
“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.
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 · see citing works
ASH, R. B. (1966) · Cited by 3,910 · see citing works
NIPS 2016 Tutorial: Generative Adversarial NetworksPreprint
Goodfellow, I. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.00160 · Cited by 1,735 · see citing works
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 · doi:10.18653/v1/d16-1244 · Cited by 1,453 · see citing works
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 1,186 · see citing works
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 · see citing works
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 · see citing works
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 · see citing works
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 · see citing works
McCarthy, J. (1960) · Cited by 799 · see citing works
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · arXiv · doi:10.48550/arxiv.1606.05250 · Cited by 678 · see citing works
Learning Deep Transformer Models for Machine Translation
Wang, Q., Li, B., Xiao, T., Zhu, J., Li, C., Wong, D. F., & Chao, L. S. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1176 · Cited by 673 · see citing works
Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data TasksPreprint
Phang, J., Févry, T., & Bowman, S. R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.01088 · Cited by 417 · see citing works
Recognizing Textual Entailment
Dagan, I., Roth, D., Sammons, M., & Zanzotto, F. M. (2013) · Synthesis lectures on human language technologies · doi:10.2200/s00509ed1v01y201305hlt023 · Cited by 281 · see citing works
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
Weston, J., Bordes, A., Chopra, S., Rush, A. M., van Merriënboer, B., Joulin, A., & Mikolov, T. (2016) · International Conference on Learning Representations · Cited by 261 · see citing works
Smodels - An Implementation of the Stable Model and Well-Founded Semantics for Normal LP
Niemelä, I., & Simons, P. (1997) · International Conference on Logic Programming · Cited by 261 · see citing works
Deep Learning for Symbolic MathematicsPreprint
Lample, G., & Charton, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.01412 · Cited by 227 · see citing works
Manning, C. D., & MacCartney, B. (2009) · Cited by 218 · see citing works
Improving Machine Reading Comprehension with General Reading Strategies
Sun, K., Yu, D., Yu, D., & Cardie, C. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1270 · Cited by 129 · see citing works
CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text
Sinha, K., Sodhani, S., Dong, J., Pineau, J., & Hamilton, W. L. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1458 · Cited by 110 · see citing works
Expert systems in production planning and scheduling: A state-of-the-art survey
Metaxiotis, K. S., Askounis, D., & Psarras, J. E. (2002) · Journal of Intelligent Manufacturing · doi:10.1023/a:1016064126976 · Cited by 98 · see citing works
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W. W., Salakhutdinov, R., & Manning, C. D. (2018) · arXiv · doi:10.48550/arxiv.1809.09600 · Cited by 97 · see citing works
Reasoning Over Paragraph Effects in Situations
Lin, K., Tafjord, O., Clark, P. E., & Gardner, M. (2019) · Workshop on Machine Reading for Question Answering (MRQA) · doi:10.18653/v1/d19-5808 · Cited by 92 · see citing works
Self-citationGeneral logical databases and programs: Default logic semantics and stratification
Bidoít, N., & Froidevaux, C. (1991) · Information and Computation · doi:10.1016/0890-5401(91)90073-b · Cited by 89 · see citing works
A Survey on Semantic ParsingPreprint
Kamath, A., & Das, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.00978 · Cited by 83 · see citing works
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
Weber, L., Minervini, P., Münchmeyer, J., Leser, U., & Rocktäschel, T. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1618 · Cited by 81 · see citing works
QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions
Tafjord, O., Gardner, M., Lin, K., & Clark, P. E. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1608 · Cited by 64 · see citing works
Self-citationJansen, P. A., Wainwright, E., Marmorstein, S., & Morrison, C. T. (2018) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/28283yn8kzpn · Cited by 56 · see citing works
He, H. W., & Choi, J. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.04943 · Cited by 37 · see citing works
Bunt, H., Bos, J., & Pulman, S. (1999) · Cited by 33 · see citing works
Natural Logic and Natural Language Inference
MacCartney, B., & Manning, C. D. (2013) · Text, speech and language technology · doi:10.1007/978-94-007-7284-7_8 · Cited by 24 · see citing works
Towards Neural Theorem Proving at ScalePreprint
Minervini, P., Bošnjak, M., Rocktäschel, T., & Riedel, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.08204 · Cited by 22 · see citing works
Improving Graph Neural Network Representations of Logical Formulae with Subgraph PoolingPreprint
Crouse, M., Abdelaziz, I., Cornelio, C., Thost, V., Wu, L., Forbus, K. D., & Fokoue, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.06904 · Cited by 22 · see citing works
Probing Natural Language Inference Models through Semantic Fragments
Richardson, K., Hu, H., Moss, L. S., & Sabharwal, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6397 · Cited by 19 · see citing works
Self-citationLearning to Reason: Leveraging Neural Networks for Approximate DNF Counting
Abboud, R., Ceylan, İ. İ., & Lukasiewicz, T. (2020) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v34i04.5705 · Cited by 17 · see citing works
Moss, L. S. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-14287-1_9 · Cited by 17 · see citing works
Musen, M. A., & van der Lei, J. (1988) · Machine intelligence and pattern recognition · doi:10.1016/b978-0-444-87137-4.50029-1 · Cited by 13 · see citing works
Differentiable Reasoning on Large Knowledge Bases and Natural Language
Minervini, P., Bošnjak, M., Rocktäschel, T., Riedel, S., & Grefenstette, E. (2020) · Studies on the semantic web · doi:10.3233/ssw200015 · Cited by 12 · see citing works
ADAPTIVE GENERATION OF PROGRAMMING PUZZLES
Kalyan, A., Polozov, O., & Kalai, A. T. (2019) · Cited by 1 · see citing works
Flagged first, then by citations
2 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
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. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505 · see citing works
“Another line of work aims to enable language models to perform logical or formal reasoning, often by verablizing the rules in natural language formal rules using language (Clark et al., 2020; Saeed et al., 2021; Liang et al., 2021).”
Text Data Augmentation for Deep Learning
Shorten, C., Khoshgoftaar, T. M., & Furht, B. (2021) · Journal Of Big Data · doi:10.1186/s40537-021-00492-0 · Cited by 1,798 · see citing works
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.04615 · Cited by 569 · see citing works
Self-citationA comprehensive survey on applications of transformers for deep learning tasks
Islam, S., Elmekki, H., Elsebai, A., Bentahar, J., Drawel, N., Rjoub, G., & Witold Pedrycz, C. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122666 · Cited by 522 · see citing works
Deep Learning applications for COVID-19
Shorten, C., Khoshgoftaar, T. M., & Furht, B. (2021) · Journal of Big Data · doi:10.1186/s40537-020-00392-9 · Cited by 350 · see citing works
Evaluating Large Language Models in Generating Synthetic HCI Research Data: a Case Study
Hämäläinen, P., Tavast, M., & Kunnari, A. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580688 · Cited by 248 · see citing works
Interactive computer-aided diagnosis on medical image using large language models
Wang, S., Zhao, Z., Ouyang, X., Liu, T., Wang, Q., & Shen, D. G. (2024) · Communications Engineering · doi:10.1038/s44172-024-00271-8 · Cited by 149 · see citing works
Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning
Pan, L., Albalak, A., Wang, X., & Wang, W. Y. (2023) · arXiv · doi:10.48550/arxiv.2305.12295 · Cited by 144 · see citing works
“Recent works in adapting large language models for logical reasoning tasks can be broadly categorized into two groups: 1) fine-tuning approaches that optimize LLMs’ reasoning ability through fine-tuning or training specialized modules (Clark et al., 2020; Tafjord et al., 2022; Yang et al., 2022), and 2) incontext lear…”
BackgroundReasoning with Language Model Prompting: A Survey
Qiao, S., Ou, Y., Zhang, N., Chen, X., Yao, Y., Deng, S., Tan, C., Huang, F., & Chen, H. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.294 · Cited by 218 · see citing works
COCO-LM: Correcting and Contrasting Text Sequences for Language Model PretrainingPreprint
Yu, M., Xiong, C., Bajaj, P., Tiwary, S., Bennett, P. N., Han, J., & Song, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08473 · Cited by 133 · see citing works
Large Language Models Can Be Easily Distracted by Irrelevant Context
Shi, F., Chen, X., Misra, K., Scales, N., Dohan, D., Chi, E., Schärli, N., & Zhou, D. (2023) · arXiv · doi:10.48550/arxiv.2302.00093 · Cited by 134 · see citing works
“There exist some logical reasoning benchmarks that contain irrelevant content in task descriptions (Weston et al., 2015; Sinha et al., 2019; Clark et al., 2021; Han et al., 2022; Tafjord et al., 2020, inter alia ).”
BackgroundFaith and Fate: Limits of Transformers on Compositionality
Dziri, N., Lu, X., Sclar, M., Li, X. (., Jiang, L., Lin, B. Y., Welleck, S., West, P., Bhagavatula, C., Bras, R. L., et al. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-3081 · Cited by 124 · see citing works
“[14] Peter Clark, Oyvind Tafjord, and Kyle Richardson.”
BackgroundFaith and Fate: Limits of Transformers on Compositionality
Dziri, N., Lu, X., Sclar, M., Li, X. L., Jiang, L., Lin, B. Y., West, P., Bhagavatula, C., Bras, R. L., Hwang, J. D., et al. (2023) · arXiv · Cited by 124 · see citing works
ProofWriter: Generating implications, proofs, and abductive statements over natural language
Tafjord, O., Dalvi, B., & Clark, P. (2021) · Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · doi:10.18653/v1/2021.findings-acl.317 · Cited by 122 · see citing works
Self-citationLevy, M., Jacoby, A., & Goldberg, Y. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.818 · Cited by 119 · see citing works
HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification
Jiang, Y., Bordia, S., Zhong, Z., Dognin, C., Singh, M., & Bansal, M. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.309 · Cited by 121 · see citing works
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo ProjectPreprint
Clark, P. E., Etzioni, O., Khashabi, D., Khot, T., Mishra, B. D., Richardson, K., Sabharwal, A., Schoenick, C., Tafjord, O., Tandon, N., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.01958 · Cited by 92 · see citing works
Self-citationGenerating Role-Playing Game Quests With GPT Language Models
Värtinen, S., Hämäläinen, P., & Guckelsberger, C. (2022) · IEEE Transactions on Games · doi:10.1109/tg.2022.3228480 · Cited by 87 · see citing works
Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond
Xu, F., Lin, Q., Han, J., Zhao, T., Liu, J., & Cambria, E. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3536008 · Cited by 76 · see citing works
Explanations for CommonsenseQA: New Dataset and Models
Aggarwal, S., Mandowara, D., Agrawal, V., Khandelwal, D., Singla, P., & Garg, D. (2021) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2021.acl-long.238 · Cited by 66 · see citing works
On the Paradox of Learning to Reason from Data
Zhang, H., Li, L. H., Meng, T., Chang, K.-W., & Broeck, G. V. D. (2022) · arXiv · doi:10.48550/arxiv.2205.11502 · Cited by 58 · see citing works
Linguistically inspired roadmap for building biologically reliable protein language models
Vu, M. H., Akbar, R., Robert, P. A., Świątczak, B., Sandve, G. K., Greiff, V., & Haug, D. T. T. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00637-1 · Cited by 57 · see citing works
Wu, Z., Qiu, L., Ross, A., Akyürek, E., Chen, B., Wang, B., Kim, N., Andreas, J., & Kim, Y. (2024) · Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2024.naacl-long.102 · Cited by 58 · see citing works
PRover: Proof Generation for Interpretable Reasoning over Rules
Saha, S., Ghosh, S., Srivastava, S., & Bansal, M. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.9 · Cited by 50 · see citing works
A Survey on Symbolic Knowledge Distillation of Large Language Models
Acharya, K., Velasquez, A., & Song, H. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3428519 · Cited by 50 · see citing works
On the Paradox of Learning to Reason from Data
Zhang, H., Li, L. H., Meng, T., Chang, K.-W., & Van den Broeck, G. (2023) · Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/375 · Cited by 58 · see citing works
Exploring Length Generalization in Large Language Models
Anil, C., Wu, Y., Andreassen, A., Lewkowycz, A., Misra, V., Ramasesh, V., Slone, A., Gur-Ari, G., Dyer, E., & Neyshabur, B. (2022) · arXiv · doi:10.48550/arxiv.2207.04901 · Cited by 44 · see citing works
“Tasks that have a reasoning component are especially well represented in this category — multi-hop reasoning [7], program execution [8], deductive reasoning [9] and theorem proving [10], to name a few.”
BackgroundKnowledge-Aware Language Model PretrainingPreprint
Rosset, C., Xiong, C., Phan, M., Song, X., Bennett, P. N., & Tiwary, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.00655 · Cited by 60 · see citing works
Are Pretrained Language Models Symbolic Reasoners over Knowledge?
Kassner, N., Krojer, B., & Schütze, H. (2020) · Conference on Computational Natural Language Learning · doi:10.18653/v1/2020.conll-1.45 · Cited by 40 · see citing works
Yoran, O., Talmor, A., & Berant, J. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.416 · Cited by 34 · see citing works
REFINER: Reasoning Feedback on Intermediate RepresentationsPreprint
Paul, D., Ismayilzada, M., Peyrard, M., Borges, B., Bosselut, A., West, R., & Faltings, B. V. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.01904 · Cited by 35 · see citing works
What Does My QA Model Know? Devising Controlled Probes Using Expert Knowledge
Richardson, K., & Sabharwal, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00331 · Cited by 35 · see citing works
Self-citationRelational World Knowledge Representation in Contextual Language Models: A Review
Safavi, T., & Koutra, D. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.81 · Cited by 37 · see citing works
Natural Language Inference in Context - Investigating Contextual Reasoning over Long Texts
Liu, H., Cui, L., Liu, J., & Zhang, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i15.17580 · Cited by 35 · see citing works
Natural Instructions: Benchmarking Generalization to New Tasks from Natural Language InstructionsPreprint
Mishra, S. R., Khashabi, D., Baral, C. R., & Hajishirzi, H. (2021) · arXiv (Cornell University) · Cited by 32 · see citing works
MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning
Jiao, F., Guo, Y., Song, X., & Nie, L. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.276 · Cited by 32 · see citing works
Generating Natural Language Proofs with Verifier-Guided Search
Yang, K., Deng, J., & Chen, D. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.7 · Cited by 29 · see citing works
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms
Zhou, P., Khanna, R., Lee, S., Lin, B. Y., Ho, D., Pujara, J., & Ren, X. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.598 · Cited by 35 · see citing works
From F to A on the New York Regents Science Exams — An Overview of the Aristo Project
Clark, P. E., Etzioni, O., Khashabi, D., Khot, T., Mishra, B. D., Richardson, K., Sabharwal, A., Schoenick, C., Tafjord, O., Tandon, N., et al. (2020) · AI Magazine · doi:10.1609/aimag.v41i4.5304 · Cited by 133 · see citing works
Self-citationEntailer: Answering Questions with Faithful and Truthful Chains of Reasoning
Tafjord, O., Mishra, B. D., & Clark, P. A. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.134 · Cited by 31 · see citing works
Self-citationBeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief
Kassner, N., Tafjord, O., Schütze, H., & Clark, P. E. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.697 · Cited by 31 · see citing works
Self-citationSay What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge
Chen, J., Shi, W., Fu, Z., Cheng, S., Li, L., & Xiao, Y. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.550 · Cited by 30 · see citing works
Logiqa 2.0—An improved dataset for logical reasoning in natural language understanding
Liu, H., Liu, J., Cui, L., Teng, Z., Duan, N., Zhou, M., & Zhang, Y. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3293046 · Cited by 26 · see citing works
Gómez-Pérez, J. M., & Ortega, R. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.441 · Cited by 23 · see citing works
Diagnosing the First-Order Logical Reasoning Ability Through LogicNLI
Tian, J., Li, Y., Chen, W., Xiao, L., He, H., & Jin, Y. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.303 · Cited by 24 · see citing works
Chinese legal judgment prediction via knowledgeable prompt learning
Sun, J., Huang, S., & Wei, C. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122177 · Cited by 24 · see citing works
Flexible Generation of Natural Language Deductions
Bostrom, K., Zhao, X., Chaudhuri, S., & Durrett, G. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.506 · Cited by 21 · see citing works
Robust and explainable identification of logical fallacies in natural language arguments
Sourati, Z., Venkatesh, V. P. P., Deshpande, D. G., Rawlani, H., Ilievski, F., Sandlin, H.-Â., & Mermoud, A. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110418 · Cited by 20 · see citing works
METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation
Hong, R., Zhang, H., Yu, X., & Zhang, C. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.145 · Cited by 21 · see citing works
BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
Kuratov, Y., Bulatov, A., Anokhin, P., Rodkin, I., Sorokin, D., Sorokin, A., & Burtsev, M. (2024) · arXiv · doi:10.48550/arxiv.2406.10149 · Cited by 19 · see citing works
“Additionally, we release the predictions of all models used in our study to ensure that all re-ported results can be reproduced and verified: https://github.com/booydar/babilong/tree/ predictions_06_2024 .”
MethodLiu, Q., Han, S., Cambria, E., Li, Y., & Kwok, K. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10345-6 · Cited by 19 · see citing works
Ortloff, A.-M., Martius, F., Meier, M., Sans-Raimbault, T., Geierhaas, L., & Smith, M. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713671 · Cited by 19 · see citing works
multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning
Saha, S., Yadav, P., & Bansal, M. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.287 · Cited by 18 · see citing works
FaiRR: Faithful and Robust Deductive Reasoning over Natural Language
Sanyal, S., Singh, H., & Ren, X. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.77 · Cited by 20 · see citing works
A Survey of Reasoning with Foundation ModelsPreprint
Sun, J., Zheng, C., Xie, E., Liu, Z., Chu, R., Liu, J., Xu, J., Ding, M., Li, H., Geng, M., et al. (2023) · doi:10.31219/osf.io/ac4sp · Cited by 51 · see citing works
Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming
Zhang, H., Huang, J., Li, Z., Naik, M., & Xing, E. P. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.191 · Cited by 23 · see citing works
RuleBERT: Teaching Soft Rules to Pre-Trained Language Models
Saeed, M., Ahmadi, N., Nakov, P., & Papotti, P. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.110 · Cited by 16 · see citing works
Generative Multi-hop Retrieval
Lee, H., Yang, S., Oh, H., & Seo, M. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.92 · Cited by 20 · see citing works
LLMs for legal reasoning: A unified framework and future perspectives
Nguyen, H.-T., Fungwacharakorn, W., Zin, M. M., Goebel, R. G., Toni, F., Stathis, K., & Satoh, K. (2025) · Computer law & security review · doi:10.1016/j.clsr.2025.106165 · Cited by 15 · see citing works
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
Zhao, J., Khashabi, D., Khot, T., Sabharwal, A., & Chang, K.-W. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.364 · Cited by 16 · see citing works
GNN is a Counter? Revisiting GNN for Question AnsweringPreprint
Wang, K., Zhang, Y., Yang, D., Song, L., & Qin, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.03192 · Cited by 16 · see citing works
Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2Preprint
Betz, G., Richardson, K., & Voigt, C. C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.13033 · Cited by 23 · see citing works
Self-citationNaturalProofs: Mathematical Theorem Proving in Natural LanguagePreprint
Welleck, S., Liu, J., Bras, R. J. L., Hajishirzi, H., Choi, Y., & Cho, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.01112 · Cited by 25 · see citing works
Exploring Transitivity in Neural NLI Models through Veridicality
Yanaka, H., Mineshima, K., & Inui, K. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.78 · Cited by 13 · see citing works
AbductionRules: Training Transformers to Explain Unexpected Inputs
Young, N., Bao, Q., Bensemann, J., & Witbrock, M. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.19 · Cited by 13 · see citing works
A BERT-based deontic logic learner
Sun, J., Huang, S., & Wei, C. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103374 · Cited by 13 · see citing works
Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning
Wang, C., Zheng, B., Niu, Y., & Zhang, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88480-2_61 · Cited by 13 · see citing works
Critical Thinking for Language ModelsPreprint
Betz, G., Voigt, C., & Richardson, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.07185 · Cited by 13 · see citing works
Self-citationPushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability
Richardson, K., & Sabharwal, A. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21371 · Cited by 12 · see citing works
Self-citationMachine Reasoning: Technology, Dilemma and Future
Duan, N., Tang, D., & Zhou, M. (2020) · doi:10.18653/v1/2020.emnlp-tutorials.1 · Cited by 12 · see citing works
Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge.Preprint
Talmor, A., Tafjord, O., Clark, P. E., Goldberg, Y., & Berant, J. (2020) · arXiv (Cornell University) · Cited by 12 · see citing works
Self-citationAnalyzing Commonsense Emergence in Few-shot Knowledge ModelsPreprint
Da, J., Bras, R. J. L., Lu, X., Choi, Y., & Bosselut, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00297 · Cited by 17 · see citing works
Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning
Mirzaee, R., & Kordjamshidi, P. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.413 · Cited by 11 · see citing works
Case-Based Reasoning with Language Models for Classification of Logical Fallacies
Sourati, Z., Ilievski, F., Sandlin, H.-Â., & Mermoud, A. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/576 · Cited by 11 · see citing works
FAQ-Based Question Answering via Knowledge Anchors
Xie, R., Lu, Y., Lin, F., & Lin, L. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60450-9_1 · Cited by 11 · see citing works
Neural Unification for Logic Reasoning over Natural Language
Picco, G., Hoang, T. L., Sbodio, M. L., & López, V. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.331 · Cited by 10 · see citing works
Yu, S. (2023) · International Academic Mindtrek Conference (Mindtrek) · doi:10.1145/3616961.3616965 · Cited by 13 · see citing works
MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic
Sileo, D., & Lernould, A. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.303 · Cited by 10 · see citing works
What About the Precedent: An Information-Theoretic Analysis of Common Law
Valvoda, J., Pimentel, T., Stoehr, N., Cotterell, R., & Teufel, S. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.181 · Cited by 10 · see citing works
Inferring Implicit Relations in Complex Questions with Language Models
Katz, U., Geva, M., & Berant, J. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.188 · Cited by 11 · see citing works
Natural Language Deduction with Incomplete Information
Sprague, Z., Bostrom, K., Chaudhuri, S., & Durrett, G. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.564 · Cited by 9 · see citing works
Exploring formal defeasible reasoning of large language models: A Chain-of-Thought approach
Li, Z., Chen, C., Li, M., & Liao, B. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113564 · Cited by 9 · see citing works
End-to-end Case-Based Reasoning for Commonsense Knowledge Base Completion
Yang, Z., Du, X., Cambria, E., & Cardie, C. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.255 · Cited by 9 · see citing works
Explainable Multi-hop Verbal Reasoning Through Internal Monologue
Liang, Z., Bethard, S. J., & Surdeanu, M. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.97 · Cited by 11 · see citing works
MindMap: Constructing Evidence Chains for Multi-Step Reasoning in Large Language Models
Wu, Y., Han, X., Song, W., Cheng, M., & Li, F. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29896 · Cited by 8 · see citing works
LoRP: LLM-based Logical Reasoning via Prolog
Di, Z., Zhang, C., Lv, H., Cui, L., & Liu, L. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114140 · Cited by 11 · see citing works
Explicit Planning Helps Language Models in Logical Reasoning
Zhao, H., Wang, K., Yu, M., & Mei, H. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.688 · Cited by 11 · see citing works
Finlayson, M., Richardson, K., Sabharwal, A., & Clark, P. A. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.27 · Cited by 8 · see citing works
Self-citationLearning Symbolic Rules for Reasoning in Quasi-Natural LanguagePreprint
Yang, K., & Deng, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12038 · Cited by 8 · see citing works
Biomedical text normalization through generative modeling
Berkowitz, J. S., Srinivasan, A., Cortina, J. M. A., Fatapour, Y., & Tatonetti, N. P. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104850 · Cited by 7 · see citing works
Coursey, K. (2020) · Springer eBooks · doi:10.1007/978-3-658-29864-7_3 · Cited by 7 · see citing works
Aghahadi, Z., & Talebpour, A. (2022) · Journal of Applied Non-Classical Logics · doi:10.1080/11663081.2022.2041352 · Cited by 7 · see citing works
Interpretable Proof Generation via Iterative Backward Reasoning
Qu, H., Cao, Y. H., Gao, J., Ding, L., & Xu, R. (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.216 · Cited by 7 · see citing works
RobustLR: A Diagnostic Benchmark for Evaluating Logical Robustness of Deductive Reasoners
Sanyal, S., Liao, Z., & Ren, X. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.653 · Cited by 11 · see citing works
Learning Paradigms for Hybrid Decision-Making Systems
Punzi, C., Pellungrini, R., Setzu, M., Giannotti, F., & Pedreschi, D. (2026) · ACM Computing Surveys · doi:10.1145/3802522 · Cited by 11 · see citing works
AlKhamissi, B., Verma, S. S., Yu, P., Jin, Z., Çelikyılmaz, A., & Diab, M. (2023) · doi:10.18653/v1/2023.nlrse-1.10 · Cited by 6 · see citing works
Betz, G., & Richardson, K. (2022) · Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/2022.starsem-1.2 · Cited by 6 · see citing works
Self-citationCan Pretrained Language Models (Yet) Reason Deductively?
Yuan, Z., Hu, S., Vulić, I., Korhonen, A., & Meng, Z. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.106 · Cited by 7 · see citing works
Conversational Neuro-Symbolic Commonsense Reasoning
Arabshahi, F., Lee, J., Gawarecki, M., Mazaitis, K., Azaria, A., & Mitchell, T. M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i6.16623 · Cited by 5 · see citing works
Discourse-Aware Graph Networks for Textual Logical Reasoning
Huang, Y., Liu, L., Xu, K., Fang, M., Lin, L., & Liang, X. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3280178 · Cited by 7 · see citing works
- 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 · 2019: 1
- 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
