Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Building on Petroni et al. (2019), we propose two new probing tasks analyzing factual knowledge stored in Pretrained Language Models (PLMs).(1) Negation.We find that PLMs do not distinguish between negated ("Birds cannot [MASK]") and non-negated ("Birds can [MASK]") cloze questions.(2) Mispriming.Inspired by priming methods in human psychology, we add "misprimes" to cloze questions ("Talk?Birds can [MASK]").We find that PLMs are easily distracted by misprimes.These results suggest that PLMs still have a long way to go to adequately learn human-like factual 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
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
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
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 · cited 4×
“T-REx, parts of ConceptNet and SQuAD allow multiple true answers (N-M).”
BackgroundInfluentialTransformer-XL: Attentive language models beyond a fixed-length context
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1285 · Cited by 3,169 · cited 3×
“PLMs like Transformer-XL (Dai et al., 2019), ELMo (Peters et al.”
BackgroundPriming and Human Memory Systems
Tulving, E., & Schacter, D. L. (1990) · Science · doi:10.1126/science.2296719 · Cited by 2,595
Natural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069
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
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
McCoy, R. T., Pavlick, E., & Linzen, T. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1334 · Cited by 944
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., & Choi, Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1470 · Cited by 904 · cited 2×
“Bosselut et al. (2019) investigate PLMs’ common sense knowledge, but do not”
Background
Cited by
Pre-trained models for natural language processing: A survey
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1647-3 · Cited by 1,591
Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference
Schick, T., & Schütze, H. (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.20 · Cited by 1,305
Self-citationKEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
Wang, X., Gao, T., Zhu, Z., Zhang, Z., Liu, Z., Li, J., & Tang, J. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00360 · Cited by 676
“This may be due to different vocabularies used in BERT and RoBERTa, which presents the vulnerability of LAMA-style probing again (Kassner and Schütze, 2020).”
MethodLin, X., Xiong, G., Gou, G., Li, Z., Shi, J., & Yu, J. (2022) · Proceedings of the ACM Web Conference 2022 · doi:10.1145/3485447.3512217 · Cited by 599
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
Yasunaga, M., Ren, H., Bosselut, A., Liang, P., & Leskovec, J. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.45 · Cited by 522
CMMLU: Measuring massive multitask language understanding in Chinese
Li, H., Zhang, Y., Koto, F., Yang, Y., Zhao, H., Gong, Y., Duan, N., & Baldwin, T. (2023) · arXiv · doi:10.48550/arxiv.2306.09212 · Cited by 464
“Previous research has pointed out that language models may struggle with negation (Kassner and Schütze, 2020; Hosseini et al., 2021).”
BackgroundK-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
Wang, R., Tang, D., Duan, N., Wei, Z., Huang, X., Ji, J., Cao, G., Jiang, D., & Zhou, M. (2021) · Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · doi:10.18653/v1/2021.findings-acl.121 · Cited by 456
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
oLMpics-On What Language Model Pre-training Captures
Talmor, A., Elazar, Y., Goldberg, Y., & Berant, J. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00342 · Cited by 271
Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP
Schick, T., Udupa, S., & Schütze, H. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00434 · Cited by 227
“Unfortunately, negation is often not understood well by current generations of language models (Kassner and Schütze, 2020).”
BackgroundSelf-citationMeasuring 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
“For instance, previous work has studied the effect of negation on factual statements, which can also be seen as consistency (Ettinger, 2020; Kassner and Schütze, 2020).”
BackgroundSelf-citationHow Context Affects Language Models' Factual Predictions
Petroni, F., Lewis, P., Piktus, A., Rocktäschel, T., Wu, Y., Miller, A. H., & Riedel, S. (2020) · arXiv · doi:10.48550/arxiv.2005.04611 · Cited by 154
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
“Similar 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,…”
BackgroundLanguage Model Behavior: A Comprehensive Survey
Chang, T. A., & Bergen, B. K. (2024) · Computational Linguistics · doi:10.1162/coli_a_00492 · Cited by 105
Few-Shot Text Generation with Natural Language Instructions
Schick, T., & Schütze, H. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.32 · Cited by 107
Self-citationMaieutic Prompting: Logically Consistent Reasoning with Recursive Explanations
Jung, J., Qin, L., Welleck, S., Brahman, F., Bhagavatula, C., Bras, R. L., & Choi, Y. (2022) · arXiv · doi:10.48550/arxiv.2205.11822 · Cited by 98
(2022) · doi:10.18653/v1/2022.emnlp-main.82 · Cited by 47
Large Language Models with Controllable Working Memory
Li, D., Rawat, A. S., Zaheer, M., Wang, X., Lukasik, M., Veit, A., Yu, F., & Kumar, S. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.112 · Cited by 46
Gubelmann, R. (2024) · Philosophy & Technology · doi:10.1007/s13347-024-00696-1 · Cited by 36
“On the other hand, they still struggle with somewhat simple semantic structures as negations, see Warstadt et al. (2020); Ettinger (2020); Kassner and Schütze (2020); Gubelmann and Handschuh (2022), and they find it difficult to master both inductive and deductive modes of inferences, see Gubelmann…”
Language models are not naysayers: an analysis of language models on negation benchmarks
Truong, T. H., Baldwin, T., Verspoor, K., & Cohn, T. (2023) · arXiv · doi:10.48550/arxiv.2306.08189 · Cited by 34
“In particular, we were inspired by the pio-neering works of Kassner and Schütze (2020) and Ettinger (2020), which reveal that pre-trained language models have a major issue in being insensitive to the presence of negation, based on evaluation over a set of cloze-style queries.”
BackgroundMethodResult“Personhood and AI: Why large language models don’t understand us”
Browning, J. (2024) · AI & SOCIETY · doi:10.1007/s00146-023-01724-y · Cited by 27
(2022) · doi:10.18653/v1/2022.emnlp-main.746 · Cited by 21
Self-citationAND does not mean OR: Using Formal Languages to Study Language Models’ Representations
Traylor, A., Feiman, R., & Pavlick, E. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) · doi:10.18653/v1/2021.acl-short.21 · Cited by 19
“, quantifiers or negation (Talmor et al., 2020; Ettinger, 2020; Kassner and Schütze, 2020; Wang et al., 2018) or by measuring the systematicity of models’ inferences (Goodwin et al.”
BackgroundThe Life Cycle of Knowledge in Big Language Models: A Survey
Cao, B., Lin, H., Han, X., & Sun, L. (2023) · arXiv · doi:10.48550/arxiv.2303.07616 · Cited by 18
The Life Cycle of Knowledge in Big Language Models: A Survey
Cao, B., Lin, H., Han, X., & Sun, L. (2024) · Machine Intelligence Research · doi:10.1007/s11633-023-1416-x · Cited by 18
This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models
García-Ferrero, I., Altuna, B., Álvez, J., Gonzalez-Dios, I., & Rigau, G. (2023) · arXiv · doi:10.48550/arxiv.2310.15941 · Cited by 18
“However, recent experiments (Kassner and Schütze, 2020; Hossain et al., 2020; Truong et al., 2022) have proven that LLMs fail at interpreting contexts in which understanding negation is required.”
BackgroundThe bewitching AI: The Illusion of Communication with Large Language Models
Bottazzi Grifoni, E., & Ferrario, R. (2025) · Philosophy & Technology · doi:10.1007/s13347-025-00893-6 · Cited by 15
Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases
Cao, B., Lin, H., Han, X., Sun, L., Yan, L., Liao, M., Xue, T., & Xu, J. (2021) · arXiv · doi:10.48550/arxiv.2106.09231 · Cited by 10
How Context Affects Language Models' Factual Predictions
Fabio Petroni, P. L. (2020) · Automated Knowledge Base Construction (AKBC) · doi:10.24432/c5201w · Cited by 4
Metadata
- Authors
- Kassner, N., & Schütze, H.
- Venue
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Published
- 2020
- Pages
- 7811-7818
- OpenAlex
- W3025064182
- Cited by
- 223
- References
- 15
- FWCI
- 17.64
- 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.