COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models
Open accessThe DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
A characteristic feature of human semantic cognition is its ability to not only store and retrieve the properties of concepts observed through experience, but to also facilitate the inheritance of properties (can breathe) from superordinate concepts (ANIMAL) to their subordinates (DOG)-i.e.demonstrate property inheritance.In this paper, we present COMPS, a collection of English minimal pair sentences that jointly tests pre-trained language models (PLMs) on their ability to attribute properties to concepts and their ability to demonstrate property inheritance behavior.Analyses of 22 different PLMs on COMPS reveal that they can easily distinguish between concepts on the basis of a property when they are trivially different, but find it relatively difficult when concepts are related on the basis of nuanced knowledge representations.Furthermore, we find that PLMs can show behaviors suggesting successful property inheritance in simple contexts, but fail in the presence of distracting information, which decreases the performance of many models sometimes even below chance.This lack of robustness in demonstrating simple reasoning raises important questions about PLMs' capacity to make correct inferences even when they appear to possess the prerequisite knowledge.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019) · arXiv · doi:10.48550/arxiv.1910.01108 · Cited by 4,653
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
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Clark, K., Luong, M.-T., Le, Q. V., & Manning, C. D. (2020) · arXiv · doi:10.48550/arxiv.2003.10555 · Cited by 1,844
Language Models as Knowledge Bases?
Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (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/d19-1250 · Cited by 1,834
Emergent Abilities of Large Language Models
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.07682 · Cited by 1,264
Designing and Interpreting Probes with Control Tasks
Hewitt, J., & Liang, P. (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/d19-1275 · Cited by 393 · cited 1×
“Apart from ongoing debates surrounding the validity of probing classifiers (see Hewitt and Liang, 2019; Ravichander et al., 2021; Belinkov, 2022), the probing setup does not allow the testing of property knowledge in a precise manner.”
BackgroundLeast-to-Most Prompting Enables Complex Reasoning in Large Language Models
Zhou, D., Schärli, N., Hou, L., Wei, J., Scales, N., Wang, X., Schuurmans, D., Cui, C., Bousquet, O., Le, Q., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.10625 · Cited by 380 · cited 1×
“, 2022b), Least-to-Most (Zhou et al., 2022), and SelfConsistency (Wang et al.”
Targeted Syntactic Evaluation of Language Models
Marvin, R., & Linzen, T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1151 · Cited by 334 · cited 1×
“The usage of minimal pairs is a well-established practice in the literature, having been widely used in works that analyze syntactic knowledge of LMs (Marvin and Linzen, 2018; Futrell et al., 2019; Warstadt et al., 2020).”
BackgroundGPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow
Black, S., Leo, G., Wang, P., Leahy, C., & Biderman, S. (2021) · Zenodo · doi:10.5281/zenodo.5297715 · Cited by 324
A Simple Method for Commonsense Reasoning
Trinh, T. H., & Le, Q. V. (2018) · arXiv · doi:10.48550/arxiv.1806.02847 · Cited by 293
Measuring and improving consistency in pretrained language models
Elazar, Y., Kassner, N., Ravfogel, S., Ravichander, A., Hovy, E., Schütze, H., & Goldberg, Y. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00410 · Cited by 220 · cited 2×
“…recently been called to question, owing to failures due to reporting bias (Gordon and Van Durme, 2013; Shwartz and Choi, 2020), lack of consistency (Elazar et al., 2021; Ravichander et al., 2020), and sensitivity to lexical cues (Kass-ner and Schütze, 2020; Misra et al., 2020; Pandia and Ettinger,…”
BackgroundResultInherent Disagreements in Human Textual Inferences
Pavlick, E., & Kwiatkowski, T. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00293 · Cited by 214
Jiang, Z., Araki, J., Ding, H., & Neubig, G. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00407 · Cited by 177 · cited 1×
“Similarly, standard cloze-testing of PLMs (Petroni et al., 2019; Weir et al., 2020; Jiang et al., 2021) also faces multiple limitations.”
BackgroundCan language models learn from explanations in context?
Lampinen, A. K., Dasgupta, I., Chan, S. C. Y., Matthewson, K., Tessler, M. H., Creswell, A., McClelland, J. L., Wang, J. X., & Hill, F. (2022) · arXiv · doi:10.48550/arxiv.2204.02329 · Cited by 163
Can language models learn from explanations in context?
Lampinen, A., Dasgupta, I., Chan, S., Mathewson, K., Tessler, M., Creswell, A., McClelland, J., Wang, J., & Hill, F. (2022) · Findings of the Association for Computational Linguistics: EMNLP 2022 · doi:10.18653/v1/2022.findings-emnlp.38 · Cited by 142
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
Self-citationProbing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?
Ravichander, A., Belinkov, Y., & Hovy, E. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.295 · Cited by 132
Word meaning in minds and machines.
Lake, B. M., & Murphy, G. L. (2023) · Psychological Review · doi:10.1037/rev0000297 · Cited by 131
Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right
Holtzman, A., West, P., Shwartz, V., Choi, Y., & Zettlemoyer, L. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.564 · Cited by 127
When Do You Need Billions of Words of Pretraining Data?
Zhang, Y., Warstadt, A., Li, X., & Bowman, S. R. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.90 · Cited by 85 · cited 1×
“Such an endeavor would require comparing performance of models across multiple checkpoints with varying number of parameters, paired with rigorous statistical inference (Sellam et al., 2021; Zhang et al., 2021).”
BackgroundCan Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Abdou, M., Kulmizev, A., Hershcovich, D., Frank, S., Pavlick, E., & Søgaard, A. (2021) · arXiv · doi:10.48550/arxiv.2109.06129 · Cited by 70 · cited 1×
“…about real world concepts and entities (Petroni et al., 2019; Weir et al., 2020, i.a. ), as well as in demonstrating isomorphism with real world abstractions like direction and color (Abdou et al., 2021; Patel and Pavlick, 2022), often times without even having been explicitly trained to do so.”
BackgroundLanguage models, like humans, show content effects on reasoning tasks
Lampinen, A. K., Dasgupta, I., Chan, S. C. Y., Sheahan, H. R., Creswell, A., Kumaran, D., McClelland, J. L., & Hill, F. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae233 · Cited by 69
Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Abdou, M., Kulmizev, A., Hershcovich, D., Frank, S., Pavlick, E., & Søgaard, A. (2021) · Proceedings of the 25th Conference on Computational Natural Language Learning · doi:10.18653/v1/2021.conll-1.9 · Cited by 64
Do Neural Language Representations Learn Physical Commonsense?
Forbes, M., Holtzman, A., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1908.02899 · Cited by 60 · cited 1×
“…different paradigms: one which uses probing classifiers to test if the applicability of a property can be decoded from the representations of LMs (Forbes et al., 2019; Da and Ka-sai, 2019; Derby et al., 2021); and the other which uses cloze-testing, in which LMs are tasked to fill in the blank in…”
MethodLanguage models show human-like content effects on reasoning tasks
Dasgupta, I., Lampinen, A. K., Chan, S. C. Y., Sheahan, H. R., Creswell, A., Kumaran, D., McClelland, J. L., & Hill, F. (2022) · arXiv · doi:10.48550/arxiv.2207.07051 · Cited by 53
The MultiBERTs: BERT Reproductions for Robustness Analysis
Sellam, T., Yadlowsky, S., Wei, J., Saphra, N., D'Amour, A., Linzen, T., Bastings, J., Turc, I., Eisenstein, J., Das, D., et al. (2021) · arXiv · doi:10.48550/arxiv.2106.16163 · Cited by 37 · cited 1×
“Such an endeavor would require comparing performance of models across multiple checkpoints with varying number of parameters, paired with rigorous statistical inference (Sellam et al., 2021; Zhang et al., 2021).”
BackgroundLampinen, A. (2024) · Computational Linguistics · doi:10.1162/coli_a_00525 · Cited by 32
Lampinen, A. K. (2022) · arXiv · doi:10.48550/arxiv.2210.15303 · Cited by 32
Understanding Commonsense Inference Aptitude of Deep Contextual Representations
Da, J., & Kasai, J. (2019) · Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing · doi:10.18653/v1/d19-6001 · Cited by 22 · cited 2×
“Contemporary work has used this dataset by taking as positive instances all concepts for which a property was generated, while taking the rest as negative instances (Lucy and Gauthier, 2017; Da and Kasai, 2019, etc.) for each property.”
BackgroundMethod
Cited by
Dissociating language and thought in large language models
Mahowald, K., Ivanova, A. A., Blank, I. A., Kanwisher, N., Tenenbaum, J. B., & Fedorenko, E. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.01.011 · Cited by 345
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
“…issues have been found for general-purpose pretrained language models, on the tasks of factual reasoning (Kassner & Sch¨utze, 2020; Pandia & Ettinger, 2021; Misra et al., 2023; Li et al., 2022), code generation (Jones & Steinhardt, 2022), and syntactic generalization (Chaves & Richter, 2021).”
BackgroundSelf-citationLanguage Model Behavior: A Comprehensive Survey
Chang, T. A., & Bergen, B. K. (2024) · Computational Linguistics · doi:10.1162/coli_a_00492 · Cited by 105
McCoy, R. T., Yao, S., Friedman, D., Hardy, M. D., & Griffiths, T. L. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2322420121 · Cited by 96
Symbols and grounding in large language models
Pavlick, E. (2023) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2022.0041 · Cited by 95
Metadata
- Authors
- Misra, K., Rayz, J., & Ettinger, A.
- Venue
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Published
- 2023
- Pages
- 2928-2949
- OpenAlex
- W4386576705
- Cited by
- 15
- References
- 33
- FWCI
- 2.84
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.