# Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuning

arXiv: https://arxiv.org/abs/2106.01207 · HTML: https://mlsanity.com/paper/2106.01207/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 55 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Revisiting Pre-Trained Models for Chinese Natural Language Processing](https://mlsanity.com/paper/2004.13922/) (2020)
- [Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/1808.09031/) (2018)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [A Systematic Assessment of Syntactic Generalization in Neural Language Models](https://mlsanity.com/paper/2005.03692/) (2020)
- [Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition](https://mlsanity.com/paper/2004.03066/) (2020)
- [Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs](https://mlsanity.com/paper/1909.02597/) (2019)
- [Cross-Linguistic Syntactic Evaluation of Word Prediction Models](https://mlsanity.com/paper/2005.00187/) (2020)
- [Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming](https://mlsanity.com/paper/2010.03010/) (2020)
- [Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages](https://mlsanity.com/paper/1903.06400/) (2019)
- [Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks](https://mlsanity.com/paper/1802.09091/) (2018)
- [Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models](https://mlsanity.com/paper/1909.10579/) (2019)
- [Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment](https://mlsanity.com/paper/2005.00165/) (2020)
- [Can LSTM Learn to Capture Agreement? The Case of Basque](https://mlsanity.com/paper/1809.04022/) (2018)
- [Harnessing the linguistic signal to predict scalar inferences](https://mlsanity.com/paper/1910.14254/) (2019)
- [Discourse structure interacts with reference but not syntax in neural language models](https://mlsanity.com/paper/2010.04887/) (2020)
- [Learning Which Features Matter: RoBERTa Acquires a Preference for Linguistic Generalizations (Eventually)](https://mlsanity.com/paper/2010.05358/) (2020)
- [A Critical Analysis of Biased Parsers in Unsupervised Parsing](https://mlsanity.com/paper/1909.09428/) (2019)

## Built on by (most cited first, 5 of 5)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Implicit causality in GPT-2: a case study](https://mlsanity.com/paper/2212.04348/) (2022)
- [Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution](https://mlsanity.com/paper/2109.13105/) (2021)
- [Advancing Perception in Artificial Intelligence through Principles of Cognitive Science](https://mlsanity.com/paper/2310.08803/) (2023)
- [Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities](https://mlsanity.com/paper/2501.12980/) (2025)

## Abstract (arXiv)

A growing body of literature has focused on detailing the linguistic knowledge embedded in large, pretrained language models. Existing work has shown that non-linguistic biases in models can drive model behavior away from linguistic generalizations. We hypothesized that competing linguistic processes within a language, rather than just non-linguistic model biases, could obscure underlying linguistic knowledge. We tested this claim by exploring a single phenomenon in four languages: English, Chinese, Spanish, and Italian. While human behavior has been found to be similar across languages, we find cross-linguistic variation in model behavior. We show that competing processes in a language act as constraints on model behavior and demonstrate that targeted fine-tuning can re-weight the learned constraints, uncovering otherwise dormant linguistic knowledge in models. Our results suggest that models need to learn both the linguistic constraints in a language and their relative ranking, with mismatches in either producing non-human-like behavior.